From 7091fd04b3ddb57dbf8c08db7ee473f35c9793dc Mon Sep 17 00:00:00 2001
From: Archit Tamarapu <archit.tamarapu@iis.fraunhofer.de>
Date: Mon, 30 Jun 2025 11:44:56 +0200
Subject: [PATCH 1/6] refactor tx configuration for processing chains

---
 examples/TEMPLATE.yml                        |  2 +-
 ivas_processing_scripts/processing/chains.py | 84 +++-----------------
 ivas_processing_scripts/processing/tx.py     | 72 +++++++++++++++++
 3 files changed, 84 insertions(+), 74 deletions(-)
 create mode 100755 ivas_processing_scripts/processing/tx.py

diff --git a/examples/TEMPLATE.yml b/examples/TEMPLATE.yml
index c6151e6a..7c8f99f6 100755
--- a/examples/TEMPLATE.yml
+++ b/examples/TEMPLATE.yml
@@ -154,7 +154,7 @@ input:
     ### REQUIRED: either error_pattern (and errpatt_late_loss_rate or errpatt_delay) or error_profile
     ### delay error profile file
     # error_pattern: ".../dly_error_profile.dat"
-    ### Late loss rate in precent or EVS
+    ### Late loss rate in precent for EVS
     # errpatt_late_loss_rate: 1
     ### Constant JBM delay in milliseconds for EVS
     # errpatt_delay: 200
diff --git a/ivas_processing_scripts/processing/chains.py b/ivas_processing_scripts/processing/chains.py
index 8e73b815..126afbdb 100755
--- a/ivas_processing_scripts/processing/chains.py
+++ b/ivas_processing_scripts/processing/chains.py
@@ -41,6 +41,7 @@ from ivas_processing_scripts.audiotools.audiofile import read, write
 from ivas_processing_scripts.processing.config import TestConfig
 from ivas_processing_scripts.processing.evs import EVS
 from ivas_processing_scripts.processing.ivas import IVAS, IVAS_rend
+from ivas_processing_scripts.processing.tx import get_tx_cfg
 from ivas_processing_scripts.processing.postprocessing import Postprocessing
 from ivas_processing_scripts.processing.preprocessing import Preprocessing
 from ivas_processing_scripts.processing.preprocessing_2 import Preprocessing2
@@ -312,52 +313,17 @@ def get_processing_chain(
         evs_lfe_9k6bps_nb = cond_cfg.get("evs_lfe_9k6bps_nb", None)
 
         # Frame error pattern bitstream modification
+        tx_cfg = None
         if "tx" in cond_cfg.keys() or hasattr(cfg, "tx"):
             # postprocess also signal without error if there is loudness scaling
             if post_cfg.get("loudness"):
                 tx_condition = True
-            # local specification overwrites global one
-            if "tx" in cond_cfg.keys():
-                tx_cfg_tmp = cond_cfg["tx"]
-            else:
-                tx_cfg_tmp = cfg.tx
-
-            if tx_cfg_tmp.get("type", None) == "FER":
-                tx_cfg = {
-                    "type": tx_cfg_tmp.get("type", None),
-                    "error_pattern": get_abs_path(
-                        tx_cfg_tmp.get("error_pattern", None)
-                    ),
-                    "error_rate": tx_cfg_tmp.get("error_rate", None),
-                    "master_seed": cfg.master_seed,
-                    "prerun_seed": cfg.prerun_seed,
-                }
-            elif tx_cfg_tmp.get("type", None) == "JBM":
-                tx_cfg = {
-                    "type": tx_cfg_tmp.get("type", None),
-                    "error_pattern": get_abs_path(
-                        tx_cfg_tmp.get("error_pattern", None)
-                    ),
-                    "errpatt_late_loss_rate": tx_cfg_tmp.get(
-                        "errpatt_late_loss_rate", None
-                    ),
-                    "errpatt_delay": tx_cfg_tmp.get("errpatt_delay", None),
-                    "errpatt_seed": tx_cfg_tmp.get("errpatt_seed", None),
-                    "error_profile": tx_cfg_tmp.get("error_profile", None),
-                    "n_frames_per_packet": tx_cfg_tmp.get("n_frames_per_packet", None),
-                    "master_seed": cfg.master_seed,
-                }
-            else:
-                raise ValueError(
-                    "Type of bitstream procesing either missing or not valid"
-                )
-        else:
-            tx_cfg = None
 
+            tx_cfg = get_tx_cfg(cfg, cond_cfg, is_EVS=True)
+
+        preamble = 0
         if hasattr(cfg, "preprocessing_2"):
             preamble = cfg.preprocessing_2.get("preamble", 0)
-        else:
-            preamble = 0
 
         # if the encoding format differs from the format after the preprocessing, add format conversion stuff
         if (cod_fmt := cod_cfg.get("fmt", tmp_in_fmt)) != tmp_in_fmt:
@@ -423,47 +389,18 @@ def get_processing_chain(
             )
 
         # Frame error pattern bitstream modification
+        tx_cfg = None
         if "tx" in cond_cfg.keys() or hasattr(cfg, "tx"):
             # postprocess also signal without error if there is loudness scaling
             if post_cfg.get("loudness"):
                 tx_condition = True
-            # local specification overwrites global one
-            if "tx" in cond_cfg.keys():
-                tx_cfg_tmp = cond_cfg["tx"]
-            else:
-                tx_cfg_tmp = cfg.tx
-
-            if tx_cfg_tmp.get("type", None) == "FER":
-                tx_cfg = {
-                    "type": tx_cfg_tmp.get("type", None),
-                    "error_pattern": get_abs_path(
-                        tx_cfg_tmp.get("error_pattern", None)
-                    ),
-                    "error_rate": tx_cfg_tmp.get("error_rate", None),
-                    "master_seed": cfg.master_seed,
-                    "prerun_seed": cfg.prerun_seed,
-                }
-            elif tx_cfg_tmp.get("type", None) == "JBM":
-                tx_cfg = {
-                    "type": tx_cfg_tmp.get("type", None),
-                    "error_pattern": tx_cfg_tmp.get("error_pattern", None),
-                    "error_profile": tx_cfg_tmp.get("error_profile", None),
-                    "n_frames_per_packet": tx_cfg_tmp.get("n_frames_per_packet", None),
-                    "master_seed": cfg.master_seed,
-                    "errpatt_seed": tx_cfg_tmp.get("errpatt_seed", None),
-                }
-                ivas_jbm = True
-            else:
-                raise ValueError(
-                    "Type of bitstream procesing either missing or not valid"
-                )
-        else:
-            tx_cfg = None
 
+            tx_cfg = get_tx_cfg(cfg, cond_cfg)
+            ivas_jbm = tx_cfg.get("type") == "JBM"
+
+        preamble = 0
         if hasattr(cfg, "preprocessing_2"):
             preamble = cfg.preprocessing_2.get("preamble", 0)
-        else:
-            preamble = 0
 
         # if the encoding format differs from the format after the preprocessing, add format conversion stuff
         if (cod_fmt := cod_cfg.get("fmt", tmp_in_fmt)) != tmp_in_fmt:
@@ -591,6 +528,7 @@ def get_processing_chain(
             }
         )
     )
+
     # add splitting and scaling for all conditions
     chain["processes"].append(
         Processing_splitting_scaling(
diff --git a/ivas_processing_scripts/processing/tx.py b/ivas_processing_scripts/processing/tx.py
new file mode 100755
index 00000000..e8f3f954
--- /dev/null
+++ b/ivas_processing_scripts/processing/tx.py
@@ -0,0 +1,72 @@
+#!/usr/bin/env python3
+
+#
+#  (C) 2022-2025 IVAS codec Public Collaboration with portions copyright Dolby International AB, Ericsson AB,
+#  Fraunhofer-Gesellschaft zur Foerderung der angewandten Forschung e.V., Huawei Technologies Co. LTD.,
+#  Koninklijke Philips N.V., Nippon Telegraph and Telephone Corporation, Nokia Technologies Oy, Orange,
+#  Panasonic Holdings Corporation, Qualcomm Technologies, Inc., VoiceAge Corporation, and other
+#  contributors to this repository. All Rights Reserved.
+#
+#  This software is protected by copyright law and by international treaties.
+#  The IVAS codec Public Collaboration consisting of Dolby International AB, Ericsson AB,
+#  Fraunhofer-Gesellschaft zur Foerderung der angewandten Forschung e.V., Huawei Technologies Co. LTD.,
+#  Koninklijke Philips N.V., Nippon Telegraph and Telephone Corporation, Nokia Technologies Oy, Orange,
+#  Panasonic Holdings Corporation, Qualcomm Technologies, Inc., VoiceAge Corporation, and other
+#  contributors to this repository retain full ownership rights in their respective contributions in
+#  the software. This notice grants no license of any kind, including but not limited to patent
+#  license, nor is any license granted by implication, estoppel or otherwise.
+#
+#  Contributors are required to enter into the IVAS codec Public Collaboration agreement before making
+#  contributions.
+#
+#  This software is provided "AS IS", without any express or implied warranties. The software is in the
+#  development stage. It is intended exclusively for experts who have experience with such software and
+#  solely for the purpose of inspection. All implied warranties of non-infringement, merchantability
+#  and fitness for a particular purpose are hereby disclaimed and excluded.
+#
+#  Any dispute, controversy or claim arising under or in relation to providing this software shall be
+#  submitted to and settled by the final, binding jurisdiction of the courts of Munich, Germany in
+#  accordance with the laws of the Federal Republic of Germany excluding its conflict of law rules and
+#  the United Nations Convention on Contracts on the International Sales of Goods.
+#
+
+from typing import Optional
+
+from ivas_processing_scripts.processing.config import TestConfig
+from ivas_processing_scripts.utils import get_abs_path
+
+
+def get_tx_cfg(cfg: TestConfig, cond_cfg: dict, is_EVS: bool = False) -> Optional[dict]:
+    # local specification overwrites global one
+    if "tx" in cond_cfg.keys():
+        tx_cfg_tmp = cond_cfg["tx"]
+    else:
+        tx_cfg_tmp = cfg.tx
+
+    if tx_cfg_tmp.get("type", None) == "FER":
+        tx_cfg = {
+            "type": tx_cfg_tmp.get("type"),
+            "error_pattern": get_abs_path(tx_cfg_tmp.get("error_pattern", None)),
+            "error_rate": tx_cfg_tmp.get("error_rate", None),
+            "master_seed": cfg.master_seed,
+            "prerun_seed": cfg.prerun_seed,
+        }
+    elif tx_cfg_tmp.get("type", None) == "JBM":
+        tx_cfg = {
+            "type": tx_cfg_tmp.get("type"),
+            "error_pattern": get_abs_path(tx_cfg_tmp.get("error_pattern", None)),
+            "errpatt_seed": tx_cfg_tmp.get("errpatt_seed", None),
+            "error_profile": tx_cfg_tmp.get("error_profile", None),
+            "n_frames_per_packet": tx_cfg_tmp.get("n_frames_per_packet", None),
+            "master_seed": cfg.master_seed,
+        }
+        # EVS specific keys
+        if is_EVS:
+            tx_cfg["errpatt_late_loss_rate"] = tx_cfg_tmp.get(
+                "errpatt_late_loss_rate", None
+            )
+            tx_cfg["errpatt_delay"] = tx_cfg_tmp.get("errpatt_delay", None)
+    else:
+        raise ValueError("Type of bitstream procesing either missing or not valid")
+
+    return tx_cfg
-- 
GitLab


From 68aa8f9079232862d5842b80ba2bf1402fa9789a Mon Sep 17 00:00:00 2001
From: Archit Tamarapu <archit.tamarapu@iis.fraunhofer.de>
Date: Tue, 1 Jul 2025 15:35:55 +0200
Subject: [PATCH 2/6] add support for discretely IVAS combined formats with two
 IVAS instances

---
 README.md                                     |  73 +++--
 ivas_processing_scripts/constants.py          |   1 +
 ivas_processing_scripts/processing/chains.py  |  85 +++---
 ivas_processing_scripts/processing/config.py  |   2 +-
 ivas_processing_scripts/processing/ivas.py    |  30 +-
 .../processing/ivas_combined.py               | 172 +++++++++++
 tests/constants.py                            |   2 +
 tests/data/test_OMASA.yml                     | 236 +++++++++++++++
 tests/data/test_OSBA.yml                      | 270 ++++++++++++++++++
 tests/test_processing.py                      |  21 ++
 10 files changed, 806 insertions(+), 86 deletions(-)
 create mode 100755 ivas_processing_scripts/processing/ivas_combined.py
 create mode 100644 tests/data/test_OMASA.yml
 create mode 100644 tests/data/test_OSBA.yml

diff --git a/README.md b/README.md
index fd03cbb2..eec184a1 100755
--- a/README.md
+++ b/README.md
@@ -1,4 +1,4 @@
-<!---
+****<!---
 
    (C) 2022-2025 IVAS codec Public Collaboration with portions copyright Dolby International AB, Ericsson AB,
    Fraunhofer-Gesellschaft zur Foerderung der angewandten Forschung e.V., Huawei Technologies Co. LTD.,
@@ -63,24 +63,24 @@ To facilitate the preparation of items for P800-{X} listening tests, it is possi
 
 ```bash
    python3 -m ivas_processing_scripts.generation path/to/scene_description_config_file.yml
- ```
- 
+```
+
 The YAML configuration file (`scene_description_config_file.yml`) defines how individual mono files should be spatially positioned and combined into the target format. For advanced formats like OMASA or OSBA, note that additional SBA items may be required. Refer to the `examples/` folder for template `.yml` files demonstrating the expected structure and usage.
 
-Relative paths are resolved from the working directory (not the YAML file location). Use absolute paths if you're unsure. Avoid using dots `.` in file names (e.g., use `item_xxa3s1.wav`, not `item.xx.a3s1.wav`). Windows users: Use double backslashes `\\` and add `.exe` to executables if needed. Input and output files follow structured naming conventions to encode metadata like lab, language, speaker ID, etc. These are explained in detail in the file under *Filename conventions*.
+Relative paths are resolved from the working directory (not the YAML file location). Use absolute paths if you're unsure. Avoid using dots `.` in file names (e.g., use `item_xxa3s1.wav`, not `item.xx.a3s1.wav`). Windows users: Use double backslashes `\\` and add `.exe` to executables if needed. Input and output files follow structured naming conventions to encode metadata like lab, language, speaker ID, etc. These are explained in detail in the file under _Filename conventions_.
 
 Each entry under `scenes:` describes one test item, specifying:
 
-* `output`: output file name
-* `description`: human-readable description
-* `input`: list of mono `.wav` files
-* `azimuth` / `elevation`: spatial placement (°)
-* `level`: loudness in dB
-* `shift`: timing offsets in seconds
+- `output`: output file name
+- `description`: human-readable description
+- `input`: list of mono `.wav` files
+- `azimuth` / `elevation`: spatial placement (°)
+- `level`: loudness in dB
+- `shift`: timing offsets in seconds
 
 Dynamic positioning (e.g., `"-20:1.0:360"`) means the source will move over time, stepping every 20 ms.
 
-The total duration of the output signal can be controlled using the  `duration` field. The output signal may optionally be rendered to the BINAURAL format by specifying the `binaural_output` field. 
+The total duration of the output signal can be controlled using the `duration` field. The output signal may optionally be rendered to the BINAURAL format by specifying the `binaural_output` field.
 
 Start by running a single scene to verify settings. Output includes both audio and optional metadata files. You can enable multiprocessing by setting `multiprocessing: true`.
 
@@ -271,6 +271,10 @@ input:
   # fmt: "7_1_4"
   ### Define mask (HP50 or 20KBP) for input signal filtering; default = null
   # mask: "HP50"
+  ### Gain factor to be applied BEFORE any other processing (linear, or add dB suffix)
+  # gain_pre: 10 dB
+  ### Gain factor to be applied AFTER any other processing (linear, or add dB suffix)
+  # gain_post: 3.1622776602
   ### Target sampling rate in Hz for resampling; default = null (no resampling)
   # fs: 16000
   ### Target loudness in LKFS; default = null (no loudness change applied)
@@ -365,14 +369,16 @@ input:
 ### List of conditions to generate
 ### Name of the key will be used as output directory name
 ###     conditions must specify the "type" key which may be one of the following options:
-###     ref        generate the reference condition
-###     lp3k5      generate a low-pass anchor with cut-off frequency 3.5 kHz
-###     lp7k       generate a low-pass anchor with cut-off frequency 7 kHz
-###     mnru       generate MNRU condition
-###     esdru      generate ESDRU condition
-###     mono_dmx   generate mono downmix condition
-###     evs        generate an EVS coded condition (see below examples for additional required keys)
-###     ivas       generate an IVAS coded condition (see below examples for additional required keys)
+###     ref             generate the reference condition
+###     lp3k5           generate a low-pass anchor with cut-off frequency 3.5 kHz
+###     lp7k            generate a low-pass anchor with cut-off frequency 7 kHz
+###     mnru            generate MNRU condition
+###     esdru           generate ESDRU condition
+###     mono_dmx        generate mono downmix condition
+###     evs             generate an EVS coded condition (see below examples for additional required keys)
+###     ivas            generate an IVAS coded condition (see below examples for additional required keys)
+###     ivas_combined   generate a combined-format IVAS coded condition using two IVAS instances for each part
+###                     (see below examples for additional required keys)
 conditions_to_generate:
   ### Reference and anchor conditions ##########################
   c01:
@@ -401,7 +407,7 @@ conditions_to_generate:
   c06:
     ### REQUIRED: type of condition
     type: ivas
-    ### REQUIRED: Bitrates to use for coding
+    ### REQUIRED: Bitrates to use for coding, for ivas_combined, first and second bitrates are for objects and spatial parts respectively
     bitrates:
       - 160000
       # - 32000
@@ -428,7 +434,7 @@ conditions_to_generate:
   c07:
     ### REQUIRED: type of condition
     type: ivas
-    ### REQUIRED: Bitrates to use for coding
+    ### REQUIRED: Bitrates to use for coding, for ivas_combined, first and second bitrates are for objects and spatial parts respectively
     bitrates:
       - 160000
       # - 32000
@@ -490,6 +496,10 @@ postprocessing:
   fmt: "BINAURAL"
   ### REQUIRED: Target sampling rate in Hz for resampling; default = null (no resampling)
   fs: 48000
+  ### Gain factor to be applied BEFORE any other processing (linear, or add dB suffix)
+  # gain_pre: 10 dB
+  ### Gain factor to be applied AFTER any other processing (linear, or add dB suffix)
+  # gain_post: 3.1622776602
   ### Low-pass cut-off frequency in Hz; default = null (no filtering)
   # lp_cutoff: 24000
   ### Target loudness in LKFS; default = null (no loudness change applied)
@@ -516,16 +526,17 @@ postprocessing:
 
 The following values may be used for the `type` key of a condition:
 
-| Supported conditions | Description                                                 |
-| :------------------: | ----------------------------------------------------------- |
-|         ref          | Uncoded (reference)                                         |
-|        lp3k5         | Uncoded low-passed at 3.5 kHz (anchor)                      |
-|         lp7k         | Uncoded low-passed at 7 kHz (anchor)                        |
-|         mnru         | Uncoded MNRU                                                |
-|        esdru         | Uncoded ESDRU                                               |
-|       mono_dmx       | Uncoded mono downmix                                        |
-|         evs          | Coded with multi-stream EVS codec (**metadata not coded!**) |
-|         ivas         | Coded with IVAS codec                                       |
+| Supported conditions | Description                                                       |
+| :------------------: | ----------------------------------------------------------------- |
+|         ref          | Uncoded (reference)                                               |
+|        lp3k5         | Uncoded low-passed at 3.5 kHz (anchor)                            |
+|         lp7k         | Uncoded low-passed at 7 kHz (anchor)                              |
+|         mnru         | Uncoded MNRU                                                      |
+|        esdru         | Uncoded ESDRU                                                     |
+|       mono_dmx       | Uncoded mono downmix                                              |
+|         evs          | Coded with multi-stream EVS codec (**metadata not coded!**)       |
+|         ivas         | Coded with IVAS codec                                             |
+|    ivas_combined     | Combined format coding with two IVAS instances (only OMASA, OSBA) |
 
 ### Configuration of conditions
 
diff --git a/ivas_processing_scripts/constants.py b/ivas_processing_scripts/constants.py
index cb51f2d7..9aa40dd4 100755
--- a/ivas_processing_scripts/constants.py
+++ b/ivas_processing_scripts/constants.py
@@ -49,6 +49,7 @@ SUPPORTED_CONDITIONS = {
     "esdru",
     "evs",
     "ivas",
+    "ivas_combined",
     "mono_dmx",
     "spatial_distortion",
 }
diff --git a/ivas_processing_scripts/processing/chains.py b/ivas_processing_scripts/processing/chains.py
index 126afbdb..f4ba665e 100755
--- a/ivas_processing_scripts/processing/chains.py
+++ b/ivas_processing_scripts/processing/chains.py
@@ -41,13 +41,14 @@ from ivas_processing_scripts.audiotools.audiofile import read, write
 from ivas_processing_scripts.processing.config import TestConfig
 from ivas_processing_scripts.processing.evs import EVS
 from ivas_processing_scripts.processing.ivas import IVAS, IVAS_rend
-from ivas_processing_scripts.processing.tx import get_tx_cfg
+from ivas_processing_scripts.processing.ivas_combined import IVASCombined
 from ivas_processing_scripts.processing.postprocessing import Postprocessing
 from ivas_processing_scripts.processing.preprocessing import Preprocessing
 from ivas_processing_scripts.processing.preprocessing_2 import Preprocessing2
 from ivas_processing_scripts.processing.processing_splitting_scaling import (
     Processing_splitting_scaling,
 )
+from ivas_processing_scripts.processing.tx import get_tx_cfg
 from ivas_processing_scripts.utils import get_abs_path, list_audio, parse_gain
 
 
@@ -63,39 +64,45 @@ def init_processing_chains(cfg: TestConfig) -> None:
     # other processing chains
     for cond_name, cond_cfg in cfg.conditions_to_generate.items():
         bitrates = cond_cfg.get("bitrates")
-        if bitrates is not None and len(bitrates) > 1:
-            multiple_bitrates_flag = True
+
+        if not bitrates:
+            # non coding condition
+            cfg.proc_chains.append(get_processing_chain(cond_name, cfg))
         else:
-            multiple_bitrates_flag = False
-        if bitrates:
-            for bitrate in bitrates:
-                # check if a list was specified
-                if isinstance(bitrate, list) and cond_name.startswith("ivas"):
-                    # flatten the list of lists for IVAS
-                    [
+            # bitrates can be a value, list or list of lists
+            # for EVS, this is a per-channel bitrate
+            # for IVAS combined, this is a per-instance bitrate
+            # otherwise it is regular IVAS with multiple bitrate conditions
+            multiple_bitrates_flag = isinstance(bitrates, list) and len(bitrates) > 1
+
+            # pass the list for IVAS Combined, per-instance bitrate
+            if cond_cfg.get("type") == "ivas_combined":
+                cfg.proc_chains.append(
+                    get_processing_chain(
+                        cond_name,
+                        cfg,
+                        bitrates,
+                    )
+                )
+            else:
+                for bitrate in bitrates:
+                    if isinstance(bitrate, list) and cond_cfg.get("type") == "ivas":
+                        # flatten the list by adding multiple conditions
+                        [
+                            cfg.proc_chains.append(
+                                get_processing_chain(
+                                    cond_name, cfg, extend_br, multiple_bitrates_flag
+                                )
+                            )
+                            for extend_br in bitrate
+                        ]
+                    else:
+                        # EVS, interpreted as per-channel bitrate
                         cfg.proc_chains.append(
                             get_processing_chain(
-                                cond_name,
-                                cond_cfg,
-                                extend_br,
-                                multiple_bitrates=multiple_bitrates_flag,
+                                cond_name, cfg, bitrate, multiple_bitrates_flag
                             )
                         )
-                        for extend_br in bitrate
-                    ]
-                else:
-                    # otherwise pass the list; EVS will interpret as per-channel bitrate
-                    cfg.proc_chains.append(
-                        get_processing_chain(
-                            cond_name,
-                            cfg,
-                            bitrate,
-                            multiple_bitrates=multiple_bitrates_flag,
-                        )
-                    )
-        else:
-            # non coding condition
-            cfg.proc_chains.append(get_processing_chain(cond_name, cfg))
 
     # list items in input directory
     cfg.items_list = list_audio(
@@ -219,12 +226,11 @@ def get_processing_chain(
 ) -> dict:
     """Mapping from test configuration to condition and postprocessing keyword arguments"""
     name = f"{condition}"
-    if bitrate:
-        if multiple_bitrates:
-            if isinstance(bitrate, list):
-                name += f"_{sum(bitrate)}"
-            else:
-                name += f"_{bitrate}"
+    if bitrate and multiple_bitrates:
+        if isinstance(bitrate, list):
+            name += f"_{sum(bitrate)}"
+        else:
+            name += f"_{bitrate}"
 
     chain = {
         "name": name,
@@ -364,7 +370,7 @@ def get_processing_chain(
         )
         # update values to reflect decoder output
         tmp_in_fs = dec_cfg.get("fs", tmp_in_fs)
-    elif cond_cfg["type"] == "ivas":
+    elif cond_cfg["type"] == "ivas" or cond_cfg["type"] == "ivas_combined":
         cod_cfg = cond_cfg["cod"]
         dec_cfg = cond_cfg["dec"]
 
@@ -402,7 +408,7 @@ def get_processing_chain(
         if hasattr(cfg, "preprocessing_2"):
             preamble = cfg.preprocessing_2.get("preamble", 0)
 
-        # if the encoding format differs from the format after the preprocessing, add format conversion stuff
+        # if the encoding format differs from the format after the preprocessing, add format conversion
         if (cod_fmt := cod_cfg.get("fmt", tmp_in_fmt)) != tmp_in_fmt:
             chain["processes"].append(
                 Postprocessing(
@@ -425,8 +431,11 @@ def get_processing_chain(
             cond_fmt.extend(tmp_out_fmt)
             tmp_out_fmt = tmp_out_fmt[0]
 
+        ivas_cls = IVAS
+        if cond_cfg["type"] == "ivas_combined":
+            ivas_cls = IVASCombined
         chain["processes"].append(
-            IVAS(
+            ivas_cls(
                 {
                     "in_fmt": tmp_in_fmt,
                     "in_fs": tmp_in_fs,
diff --git a/ivas_processing_scripts/processing/config.py b/ivas_processing_scripts/processing/config.py
index 233625f4..bf852607 100755
--- a/ivas_processing_scripts/processing/config.py
+++ b/ivas_processing_scripts/processing/config.py
@@ -230,7 +230,7 @@ class TestConfig:
                     raise KeyError(
                         f"The following key(s) must be specified for EVS: {REQUIRED_KEYS_EVS}"
                     )
-            elif type == "ivas":
+            elif type == "ivas" or type == "ivas_combined":
                 merged_cfg = get_default_config_for_codecs("IVAS", codec_bin_extension)
                 merge_dicts(merged_cfg, cond_cfg)
                 cfg["conditions_to_generate"][cond_name] = merged_cfg
diff --git a/ivas_processing_scripts/processing/ivas.py b/ivas_processing_scripts/processing/ivas.py
index faaf40f9..92c189cc 100755
--- a/ivas_processing_scripts/processing/ivas.py
+++ b/ivas_processing_scripts/processing/ivas.py
@@ -54,13 +54,13 @@ from ivas_processing_scripts.utils import run, use_wine
 class IVAS(Processing):
     def __init__(self, attrs):
         super().__init__(attrs)
-        self._validate()
         self.name = "ivas"
         self.in_fmt = audio.fromtype(self.in_fmt)
         self.out_fmt = audio.fromtype(self.out_fmt)
         if not hasattr(self, "dec_opts"):
             self.dec_opts = None
         self._use_wine = use_wine(self.use_windows_codec_binaries)
+        self._validate()
 
     def _validate(self):
         need_exe_suffix = (
@@ -146,21 +146,19 @@ class IVAS(Processing):
         logger.debug(f"IVAS encoder {in_file} -> {bitstream}")
 
         # Only resample and convert if wav, otherwise supposed pcm to be sampled at self.in_fs
-        metadata_files = []
-
-        # for MASA suppose that metadata file has same basename and location as input file
-        if isinstance(self.in_fmt, audio.MetadataAssistedSpatialAudio):
-            md_file = in_file.parent / (in_file.name + ".met")
-            metadata_files.append(md_file)
-        elif isinstance(self.in_fmt, (audio.ObjectBasedAudio, audio.OSBAAudio)):
-            metadata_files = in_meta
-        elif isinstance(self.in_fmt, audio.OMASAAudio):
-            metadata_files = in_meta
-            # TODO treffehn: check and maybe change here and for masa
-            # if len(metadata_files) != number of ism channels plus one
-            # md_file = in_file.parent / (in_file.name + ".met")
-            # metadata_files.append(md_file)
-            pass
+        metadata_files = in_meta if in_meta else []
+
+        if not metadata_files:
+            if isinstance(self.in_fmt, audio.MetadataAssistedSpatialAudio):
+                md_file = in_file.parent / (in_file.name + ".met")
+                metadata_files = [md_file]
+            elif isinstance(self.in_fmt, (audio.ObjectBasedAudio, audio.OSBAAudio)):
+                metadata_files = in_meta
+            elif isinstance(self.in_fmt, audio.OMASAAudio):
+                metadata_files = in_meta
+                if len(metadata_files) != self.in_fmt.num_ism_channels + 1:
+                    md_file = in_file.parent / (in_file.name + ".met")
+                    metadata_files.append(md_file)
 
         # Support input file wav, pcm and txt (metadata iis)
         if in_file.suffix == ".wav":
diff --git a/ivas_processing_scripts/processing/ivas_combined.py b/ivas_processing_scripts/processing/ivas_combined.py
new file mode 100755
index 00000000..b2caf2b4
--- /dev/null
+++ b/ivas_processing_scripts/processing/ivas_combined.py
@@ -0,0 +1,172 @@
+#!/usr/bin/env python3
+
+#
+#  (C) 2022-2025 IVAS codec Public Collaboration with portions copyright Dolby International AB, Ericsson AB,
+#  Fraunhofer-Gesellschaft zur Foerderung der angewandten Forschung e.V., Huawei Technologies Co. LTD.,
+#  Koninklijke Philips N.V., Nippon Telegraph and Telephone Corporation, Nokia Technologies Oy, Orange,
+#  Panasonic Holdings Corporation, Qualcomm Technologies, Inc., VoiceAge Corporation, and other
+#  contributors to this repository. All Rights Reserved.
+#
+#  This software is protected by copyright law and by international treaties.
+#  The IVAS codec Public Collaboration consisting of Dolby International AB, Ericsson AB,
+#  Fraunhofer-Gesellschaft zur Foerderung der angewandten Forschung e.V., Huawei Technologies Co. LTD.,
+#  Koninklijke Philips N.V., Nippon Telegraph and Telephone Corporation, Nokia Technologies Oy, Orange,
+#  Panasonic Holdings Corporation, Qualcomm Technologies, Inc., VoiceAge Corporation, and other
+#  contributors to this repository retain full ownership rights in their respective contributions in
+#  the software. This notice grants no license of any kind, including but not limited to patent
+#  license, nor is any license granted by implication, estoppel or otherwise.
+#
+#  Contributors are required to enter into the IVAS codec Public Collaboration agreement before making
+#  contributions.
+#
+#  This software is provided "AS IS", without any express or implied warranties. The software is in the
+#  development stage. It is intended exclusively for experts who have experience with such software and
+#  solely for the purpose of inspection. All implied warranties of non-infringement, merchantability
+#  and fitness for a particular purpose are hereby disclaimed and excluded.
+#
+#  Any dispute, controversy or claim arising under or in relation to providing this software shall be
+#  submitted to and settled by the final, binding jurisdiction of the courts of Munich, Germany in
+#  accordance with the laws of the Federal Republic of Germany excluding its conflict of law rules and
+#  the United Nations Convention on Contracts on the International Sales of Goods.
+#
+
+import logging
+import platform
+from pathlib import Path
+from warnings import warn
+
+from ivas_processing_scripts.audiotools import audio
+from ivas_processing_scripts.audiotools.audiofile import read, write
+from ivas_processing_scripts.audiotools.wrappers.eid_xor import (
+    validate_error_pattern_application,
+)
+from ivas_processing_scripts.audiotools.wrappers.networkSimulator import (
+    validate_network_simulator,
+)
+from ivas_processing_scripts.processing.ivas import IVAS
+from ivas_processing_scripts.processing.processing import Processing
+from ivas_processing_scripts.utils import use_wine
+
+
+class IVASCombined(Processing):
+    def __init__(self, attrs):
+        super().__init__(attrs)
+        self.name = "ivas_combined"
+        self.in_fmt = audio.fromtype(self.in_fmt)
+        self.out_fmt = audio.fromtype(self.out_fmt)
+        if not hasattr(self, "dec_opts"):
+            self.dec_opts = None
+        self._use_wine = use_wine(self.use_windows_codec_binaries)
+        self._validate()
+
+        # initialisation of internal IVAS instances
+        self.ivas_objects = IVAS(
+            dict(attrs, in_fmt=self.in_fmt_objects, bitrate=self.object_bitrate)
+        )
+        self.ivas_spatial = IVAS(
+            dict(attrs, in_fmt=self.in_fmt_spatial, bitrate=self.spatial_bitrate)
+        )
+
+    def _validate(self):
+        need_exe_suffix = (
+            platform.system() == "Windows" or self.use_windows_codec_binaries
+        )
+        if not self.cod_bin or not Path(self.cod_bin).exists():
+            if need_exe_suffix and (
+                self.cod_bin and Path(self.cod_bin).with_suffix(".exe").exists()
+            ):
+                self.cod_bin = Path(self.cod_bin).with_suffix(".exe")
+            else:
+                raise FileNotFoundError(
+                    "The IVAS encoder binary was not found! Please check the configuration."
+                )
+        if not self.dec_bin or not Path(self.dec_bin).exists():
+            if need_exe_suffix and (
+                self.dec_bin and Path(self.dec_bin).with_suffix(".exe").exists()
+            ):
+                self.dec_bin = Path(self.dec_bin).with_suffix(".exe")
+            else:
+                raise FileNotFoundError(
+                    "The IVAS decoder binary was not found! Please check the configuration."
+                )
+
+        # existence of error pattern files (if given) already here
+        if self.tx is not None:
+            if self.tx.get("type", None) == "JBM":
+                validate_network_simulator(
+                    self.tx["error_pattern"],
+                    self.tx["error_profile"],
+                    self.tx["n_frames_per_packet"],
+                )
+            elif self.tx.get("type", None) == "FER":
+                validate_error_pattern_application(
+                    self.tx["error_pattern"],
+                    self.tx["error_rate"],
+                )
+
+        if not isinstance(self.in_fmt, (audio.OSBAAudio, audio.OMASAAudio)):
+            raise ValueError(
+                f"IVAS discrete combined format coding only supported for OMASA or OSBA, specified format: {self.in_fmt.name}"
+            )
+
+        # set object and spatial format
+        self.in_fmt_objects = self.in_fmt.name[:4]
+        self.in_fmt_spatial = self.in_fmt.name[4:]
+
+        # set object and spatial bitrates
+        if not isinstance(self.bitrate, list) or len(self.bitrate) not in [1, 2]:
+            raise ValueError(
+                "IVAS discrete combined format coding requires a list of two bitrates, one for each IVAS instance"
+            )
+
+        self.object_bitrate, *spatial_bitrate = self.bitrate
+
+        if len(spatial_bitrate) == 0:
+            warn(
+                "Only one bitrate provided; using it for both object and spatial bitrates."
+            )
+
+        self.spatial_bitrate = (
+            spatial_bitrate[0] if spatial_bitrate else self.object_bitrate
+        )
+
+    def process(
+        self, in_file: Path, out_file: Path, in_meta, logger: logging.Logger
+    ) -> None:
+
+        logger.debug(f"IVAS configuration : {self.__dict__}")
+        logger.debug(f"IVAS {in_file.absolute()} -> {out_file.absolute()}")
+
+        # split into objects and spatial files
+        in_file_objects = in_file.with_suffix(f".objects{in_file.suffix}")
+        in_file_spatial = in_file.with_suffix(f".spatial{in_file.suffix}")
+
+        in_audio, fs = read(in_file)
+        write(in_file_objects, in_audio[:, : self.in_fmt.num_ism_channels], fs)
+        write(in_file_spatial, in_audio[:, self.in_fmt.num_ism_channels :], fs)
+
+        out_file_objects = out_file.with_suffix(f".objects{out_file.suffix}")
+        out_file_spatial = out_file.with_suffix(f".spatial{out_file.suffix}")
+
+        in_meta_objects = in_meta[: self.in_fmt.num_ism_channels]
+        in_meta_spatial = in_meta[self.in_fmt.num_ism_channels :]
+
+        # coding
+        self.ivas_objects.process(
+            in_file_objects, out_file_objects, in_meta_objects, logger
+        )
+        self.ivas_spatial.process(
+            in_file_spatial, out_file_spatial, in_meta_spatial, logger
+        )
+
+        out_audio_objects, fs = read(out_file_objects)
+        out_audio_spatial, fs = read(out_file_spatial)
+
+        # combine outputs, with gain factor if OSBA
+        if isinstance(self.in_fmt, audio.OSBAAudio):
+            out_audio_objects *= 0.5
+            out_audio_spatial *= 0.5
+
+        out_audio = out_audio_objects + out_audio_spatial
+
+        write(out_file, out_audio, fs)
diff --git a/tests/constants.py b/tests/constants.py
index 2bf642e6..fe9dace9 100644
--- a/tests/constants.py
+++ b/tests/constants.py
@@ -217,6 +217,8 @@ INPUT_CONFIG_FILES = [
     "test_ISM.yml",
     "test_MASA.yml",
     "test_MC.yml",
+    "test_OMASA.yml",
+    "test_OSBA.yml",
     "test_SBA.yml",
 ]
 
diff --git a/tests/data/test_OMASA.yml b/tests/data/test_OMASA.yml
new file mode 100644
index 00000000..ec294cff
--- /dev/null
+++ b/tests/data/test_OMASA.yml
@@ -0,0 +1,236 @@
+################################################
+# General configuration
+################################################
+### Name of test; default = YYYYMMDD_HH.MM.SS_listening_test
+# name: test SBA
+### Date; default = YYYYMMDD_HH.MM.SS
+# date: 2023.06.30
+### git commit SHA; default = git rev-parse HEAD
+# git_sha: abc123
+
+### Whether to use multiprocessing; default = true
+# multiprocessing: false
+### Deletion of temporary directories containing
+### intermediate processing files, bitstreams etc.; default = false
+# delete_tmp: true
+### Deletion of output_path if it exists
+### WARNING! Use with caution and only for debugging test setup issues!; default = false
+delete_output: false
+### Master seed for random processes like bitstream error pattern generation; default = 0
+master_seed: 5
+### Any relative paths will be interpreted relative to the working directory the script is called from!
+### Usage of absolute paths is recommended.
+### Do not use file names with dots "." in them! This is not supported, use "_" instead
+### For Windows user: please use double back slash '\\' in paths and add '.exe' to executable definitions
+### REQUIRED: Input path or file
+input_path: "./tests/concatenation_folder/OMASA"
+### REQUIRED: Output path or file
+output_path: "./tests/temp_output_OMASA"
+### Metadata path or file(s)
+### If input format is ISM{1-4} a path for the metadata files can be specified;
+### default = null (for ISM search for item_name.{wav, raw, pcm}.{0-3}.csv in input folder, otherise ignored)
+# metadata_path:
+### Path can be set for all items with the 'all_items' key (automatic search for item_name.{wav, raw, pcm}.{0-3}.csv within this folder)
+# all_items: ".../metadata_folder"
+### Path can be set for all items individually with 'item{1-4}' keys
+### 'item{1-4}' keys can also be renamed to the input file names including extension {wav, raw, pcm}
+### Either list individual files for all objects or name folder for automatic search for one item
+# item1:
+# - ".../meta_all_obj"
+# item2:
+# - ".../meta_obj1.csv"
+# - ".../meta_ob2.csv"
+# noise.wav:
+# - ".../metadata_folder_for_noise_item"
+
+### Select only a subset of items
+### searches for the specified substring in found filenames; default = null
+# input_select:
+#  - "48kHz"
+
+################################################
+### Input configuration
+################################################
+input:
+    ### REQUIRED: Input format
+    fmt: "ISM4MASA2DIR2"
+    ### Input sampling rate in Hz needed for headerless audio files; default = 48000
+    # fs: 32000
+################################################
+### Pre-processing on individual items
+################################################
+### Pre-processing step performed prior to core processing for all conditions
+### If not defined, preprocessing step is skipped
+preprocessing:
+    ### Linear gain factor to be applied before any other processing
+    gain: 3.1622776602
+    ### Target format used in rendering from input format; default = null (no rendering)
+    # fmt: "7_1_4"
+    ### Define mask (HP50 or 20KBP) for input signal filtering; default = null
+    mask: "HP50"
+    ### Target sampling rate in Hz for resampling; default = null (no resampling)
+    # fs: 32000
+    ### Target loudness in LKFS; default = null (no loudness change applied)
+    loudness: -30
+    ### Spatial audio format in which loudness is adjusted (only used if preprocessing loudness is not null);
+    ### default = null (uses preprocessing fmt if possible)
+    # loudness_fmt: "MONO"
+    ### Pre-/post-trim individual signal(s) (ms) (negative values pad silence); default = 0
+    # trim:
+    # - 50
+    # - -50
+    ### Flag for using noise (amplitude +-4) instead of silence for padding; default = false (silence)
+    # pad_noise: true
+    ### Value for application of delay (ms) (negative values advance); default = 0
+    # delay: 20
+    ### Length of window used at start/end of signal (ms); default = 0
+    window: 100
+################################################
+### Pre-processing on whole signal(s)
+################################################
+preprocessing_2:
+    ### Options for processing of the concatenated item (concatenate_input: true) or
+    ### the individual items (concatenate_input: false) after previous pre-processing step
+    ### Horizontally concatenate input items into one long file; default = false
+    # concatenate_input: true
+    ### Specify the concatenation order in a list of strings. If not specified, the concatenation order would be
+    ### as per the filesystem on the users' device
+    ### Should only be used if concatenate_input = true
+    ### Specify the filename with extension.
+    ### For example, concatenation_order: ["file3.wav", "file1.wav", "file4.wav", "file2.wav"]
+    # concatenation_order: []
+    ### Specify preamble duration in ms; default = 0
+#   preamble: 10000
+### Flag wheter to use noise (amplitude +-4) for the preamble or silence; default = false (silence)
+#   preamble_noise: true
+### Additive background noise
+# background_noise:
+### REQUIRED: SNR for background noise in dB
+# snr: 10
+### REQUIRED: Path to background noise, must have same format and sampling rate as input signal(s)
+# background_noise_path: ".../noise.wav"
+### Seed for delay offest; default = 0
+# seed_delay: 10
+#################################################
+### Bitstream processing
+#################################################
+### Bitstream processing (transport simulation) done after encoding and before decoding
+### e.g. frame error insertion or transport simulation for JBM testing
+### can be given globally here or in individual conditions of type ivas or evs
+# tx:
+### REQUIRED: Type of bitstream processing; possible types: "JBM" or "FER"
+# type: "JBM"
+
+### JBM
+### REQUIRED: either error_pattern or error_profile
+### delay error profile file
+# error_pattern: ".../dly_error_profile.dat"
+### Index of one of the existing delay error profile files to use (1-11)
+# error_profile: 5
+## nFramesPerPacket parameter for the network simulator; default = 1
+# n_frames_per_packet: 2
+
+### FER
+### REQUIRED: either error_pattern or error_rate
+### Frame error pattern file
+# error_pattern: "path/pattern.192"
+### Error rate in percent
+# error_rate: 5
+### Additional seed to specify number of preruns; default = 0
+# prerun_seed: 2
+
+################################################
+### Configuration for conditions under test
+################################################
+### List of conditions to generate
+### Name of the key will be used as output directory name
+###     conditions must specify the "type" key which may be one of the following options:
+###     ref        generate the reference condition
+###     lp3k5      generate a low-pass anchor with cut-off frequency 3.5 kHz
+###     lp7k       generate a low-pass anchor with cut-off frequency 7 kHz
+###     mnru       generate MNRU condition
+###     esdru      generate ESDRU condition
+###     mono_dmx   generate mono downmix condition
+###     evs        generate an EVS coded condition (see below examples for additional required keys)
+###     ivas       generate an IVAS coded condition (see below examples for additional required keys)
+conditions_to_generate:
+    ### Reference and anchor conditions ##########################
+    c01:
+        ### REQUIRED: type of condition
+        type: ref
+        ### optional low-pass cut-off frequency in Hz; default = null
+        # out_fc: 22500
+    c02:
+        ### REQUIRED: type of condition
+        type: lp7k
+    c03:
+        ### REQUIRED: type of condition
+        type: mnru
+        ### REQUIRED: the ratio of speech power to modulated noise power in dB
+        q: 20
+    c04:
+        ### REQUIRED: type of condition
+        type: esdru
+        ### REQUIRED: spatial degradation value between 0 and 1
+        alpha: 0.5
+    ### IVAS condition ###############################
+    c06:
+        ### REQUIRED: type of condition
+        type: ivas
+        ### REQUIRED: Bitrates to use for coding
+        bitrates:
+            - 160000
+        ### Encoder options
+        cod:
+        ### Decoder options
+        dec:
+            fmt: "BINAURAL"
+        ### Bitstream options
+        # tx:
+        ### For possible arguments see overall bitstream modification
+    ### IVAS condition ###############################
+    c07:
+        ### REQUIRED: type of condition
+        type: ivas_combined
+        ### REQUIRED: Bitrates to use for coding
+        bitrates:
+            - 128000
+            - 64000
+    ### EVS condition ################################
+    c08:
+        ### REQUIRED: type of condition
+        type: evs
+        ### REQUIRED: Bitrates to use for coding
+        ### For EVS mono, this may be a per-channel bitrate configuration (must match input/preprocessing format!)
+        ### the last value will be repeated if too few are specified
+        bitrates:
+            # - 9600
+            - [13200, 13200, 8000, 13200, 9600]
+################################################
+### Post-processing
+################################################
+### Post-processing step performed after core processing for all conditions
+### Post-processing is required and can not be omitted
+postprocessing:
+    ### REQUIRED: Target format for output
+    fmt: "BINAURAL"
+    ### REQUIRED: Target sampling rate in Hz for resampling
+    fs: 48000
+    ### Linear gain factor to be applied before any other processing
+    gain: 0.316227766
+    ### Low-pass cut-off frequency in Hz; default = null (no filtering)
+    # lp_cutoff: 24000
+    ### Target loudness in LKFS; default = null (no loudness change applied)
+    loudness: -26
+    ### Spatial audio format in which loudness is adjusted (only used if preprocessing loudness is not null);
+    ### default = null (uses postprocessing fmt if possible)
+    # loudness_fmt: null
+    ### Name of custom binaural dataset (without prefix or suffix);
+    ### default = null (ORANGE53(_Dolby) for BINAURAL, IISofficialMPEG222UC for BINAURAL_ROOM)
+    # bin_dataset: SADIE
+    ### Render LFE to binaural output with the specified gain (only valid for channel-based input); default = null
+    # bin_lfe_gain: 1
+    ### Flag whether output should be limited to avoid clipping (can alter target loudness); default = false
+    limit: true
+    ### Head-tracking trajectory file for binaural output; default = null
+    # trajectory: "path/to/file"
diff --git a/tests/data/test_OSBA.yml b/tests/data/test_OSBA.yml
new file mode 100644
index 00000000..3ff45da0
--- /dev/null
+++ b/tests/data/test_OSBA.yml
@@ -0,0 +1,270 @@
+################################################
+# General configuration
+################################################
+### Name of test; default = YYYYMMDD_HH.MM.SS_listening_test
+# name: test SBA
+### Date; default = YYYYMMDD_HH.MM.SS
+# date: 2023.06.30
+### git commit SHA; default = git rev-parse HEAD
+# git_sha: abc123
+
+### Whether to use multiprocessing; default = true
+# multiprocessing: false
+### Deletion of temporary directories containing
+### intermediate processing files, bitstreams etc.; default = false
+# delete_tmp: true
+### Deletion of output_path if it exists
+### WARNING! Use with caution and only for debugging test setup issues!; default = false
+delete_output: false
+### Master seed for random processes like bitstream error pattern generation; default = 0
+master_seed: 5
+### Any relative paths will be interpreted relative to the working directory the script is called from!
+### Usage of absolute paths is recommended.
+### Do not use file names with dots "." in them! This is not supported, use "_" instead
+### For Windows user: please use double back slash '\\' in paths and add '.exe' to executable definitions
+### REQUIRED: Input path or file
+input_path: "./tests/concatenation_folder/OSBA"
+### REQUIRED: Output path or file
+output_path: "./tests/temp_output_OSBA"
+### Metadata path or file(s)
+### If input format is ISM{1-4} a path for the metadata files can be specified;
+### default = null (for ISM search for item_name.{wav, raw, pcm}.{0-3}.csv in input folder, otherise ignored)
+# metadata_path:
+### Path can be set for all items with the 'all_items' key (automatic search for item_name.{wav, raw, pcm}.{0-3}.csv within this folder)
+# all_items: ".../metadata_folder"
+### Path can be set for all items individually with 'item{1-4}' keys
+### 'item{1-4}' keys can also be renamed to the input file names including extension {wav, raw, pcm}
+### Either list individual files for all objects or name folder for automatic search for one item
+# item1:
+# - ".../meta_all_obj"
+# item2:
+# - ".../meta_obj1.csv"
+# - ".../meta_ob2.csv"
+# noise.wav:
+# - ".../metadata_folder_for_noise_item"
+
+### Select only a subset of items
+### searches for the specified substring in found filenames; default = null
+# input_select:
+#  - "48kHz"
+
+################################################
+### Input configuration
+################################################
+input:
+    ### REQUIRED: Input format
+    fmt: "ISM4SBA3"
+    ### Input sampling rate in Hz needed for headerless audio files; default = 48000
+    # fs: 32000
+################################################
+### Pre-processing on individual items
+################################################
+### Pre-processing step performed prior to core processing for all conditions
+### If not defined, preprocessing step is skipped
+preprocessing:
+    ### Linear gain factor to be applied before any other processing
+    gain: 3.1622776602
+    ### Target format used in rendering from input format; default = null (no rendering)
+    # fmt: "7_1_4"
+    ### Define mask (HP50 or 20KBP) for input signal filtering; default = null
+    mask: "HP50"
+    ### Target sampling rate in Hz for resampling; default = null (no resampling)
+    fs: 32000
+    ### Target loudness in LKFS; default = null (no loudness change applied)
+    loudness: -26
+    ### Spatial audio format in which loudness is adjusted (only used if preprocessing loudness is not null);
+    ### default = null (uses preprocessing fmt if possible)
+    loudness_fmt: "MONO"
+    ### Pre-/post-trim individual signal(s) (ms) (negative values pad silence); default = 0
+    # trim:
+    # - 50
+    # - -50
+    ### Flag for using noise (amplitude +-4) instead of silence for padding; default = false (silence)
+    # pad_noise: true
+    ### Value for application of delay (ms) (negative values advance); default = 0
+    # delay: 20
+    ### Length of window used at start/end of signal (ms); default = 0
+    window: 100
+################################################
+### Pre-processing on whole signal(s)
+################################################
+preprocessing_2:
+    ### Options for processing of the concatenated item (concatenate_input: true) or
+    ### the individual items (concatenate_input: false) after previous pre-processing step
+    ### Horizontally concatenate input items into one long file; default = false
+    concatenate_input: true
+    ### Specify the concatenation order in a list of strings. If not specified, the concatenation order would be
+    ### as per the filesystem on the users' device
+    ### Should only be used if concatenate_input = true
+    ### Specify the filename with extension.
+    ### For example, concatenation_order: ["file3.wav", "file1.wav", "file4.wav", "file2.wav"]
+    # concatenation_order: []
+    ### Specify preamble duration in ms; default = 0
+    preamble: 10000
+    ### Flag wheter to use noise (amplitude +-4) for the preamble or silence; default = false (silence)
+    # preamble_noise: true
+    ### Additive background noise
+    # background_noise:
+    ### REQUIRED: SNR for background noise in dB
+    # snr: 10
+    ### REQUIRED: Path to background noise, must have same format and sampling rate as input signal(s)
+    # background_noise_path: ".../noise.wav"
+    ### Seed for delay offest; default = 0
+    # seed_delay: 10
+#################################################
+### Bitstream processing
+#################################################
+### Bitstream processing (transport simulation) done after encoding and before decoding
+### e.g. frame error insertion or transport simulation for JBM testing
+### can be given globally here or in individual conditions of type ivas or evs
+# tx:
+### REQUIRED: Type of bitstream processing; possible types: "JBM" or "FER"
+# type: "JBM"
+
+### JBM
+### REQUIRED: either error_pattern or error_profile
+### delay error profile file
+# error_pattern: ".../dly_error_profile.dat"
+### Index of one of the existing delay error profile files to use (1-11)
+# error_profile: 5
+## nFramesPerPacket parameter for the network simulator; default = 1
+# n_frames_per_packet: 2
+
+### FER
+### REQUIRED: either error_pattern or error_rate
+### Frame error pattern file
+# error_pattern: "path/pattern.192"
+### Error rate in percent
+# error_rate: 5
+### Additional seed to specify number of preruns; default = 0
+# prerun_seed: 2
+
+################################################
+### Configuration for conditions under test
+################################################
+### List of conditions to generate
+### Name of the key will be used as output directory name
+###     conditions must specify the "type" key which may be one of the following options:
+###     ref        generate the reference condition
+###     lp3k5      generate a low-pass anchor with cut-off frequency 3.5 kHz
+###     lp7k       generate a low-pass anchor with cut-off frequency 7 kHz
+###     mnru       generate MNRU condition
+###     esdru      generate ESDRU condition
+###     mono_dmx   generate mono downmix condition
+###     evs        generate an EVS coded condition (see below examples for additional required keys)
+###     ivas       generate an IVAS coded condition (see below examples for additional required keys)
+conditions_to_generate:
+    ### Reference and anchor conditions ##########################
+    c01:
+        ### REQUIRED: type of condition
+        type: ref
+        ### optional low-pass cut-off frequency in Hz; default = null
+        # out_fc: 22500
+    c02:
+        ### REQUIRED: type of condition
+        type: lp3k5
+    c03:
+        ### REQUIRED: type of condition
+        type: mnru
+        ### REQUIRED: the ratio of speech power to modulated noise power in dB
+        q: 20
+    c04:
+        ### REQUIRED: type of condition
+        type: esdru
+        ### REQUIRED: spatial degradation value between 0 and 1
+        alpha: 0.5
+    c05:
+        ### REQUIRED: type of condition
+        type: mono_dmx
+    ### IVAS condition ###############################
+    c06:
+        ### REQUIRED: type of condition
+        type: ivas
+        ### REQUIRED: Bitrates to use for coding
+        bitrates:
+        - 64000
+        ### Encoder options
+        cod:
+            fmt: "ISM4SBA3"
+        ### Decoder options
+        dec:
+            fmt: "BINAURAL"
+    ### IVAS condition ###############################
+    c07:
+        ### REQUIRED: type of condition
+        type: ivas
+        ### REQUIRED: Bitrates to use for coding
+        bitrates:
+        - 64000
+        ### Encoder options
+        cod:
+        ### Decoder options
+        dec:
+        fmt: "HOA3"
+        ### Bitstream options
+        tx:
+        ### For possible arguments see overall bitstream modification
+            type: "FER"
+            error_rate: 3
+            prerun_seed: 2
+    c08:
+        ### REQUIRED: type of condition
+        type: ivas_combined
+        ### REQUIRED: Bitrates to use for coding
+        bitrates:
+        - 32000
+        - 32000
+        ### Encoder options
+        cod:
+        ### Decoder options
+        dec:
+        fmt: "BINAURAL"
+    ### EVS condition ################################
+    c09:
+        ### REQUIRED: type of condition
+        type: evs
+        ### REQUIRED: Bitrates to use for coding
+        ### For EVS mono, this may be a per-channel bitrate configuration (must match input/preprocessing format!)
+        ### the last value will be repeated if too few are specified
+        bitrates:
+        # - 9600
+        - [13200, 13200, 8000, 13200, 9600]
+        cod:
+        fmt: "PLANARFOA"
+        ### Path to encoder binary; default search for EVS_cod in bin folder (primary) and PATH (secondary)
+        #bin: EVS_cod
+        ### Encoder input sampling rate in Hz (resampling performed in case of mismatch); default = null (no resampling)
+        # fs: 32000
+        dec:
+        ### Path to encoder binary; default search for EVS_dec in bin folder (primary) and PATH (secondary)
+        #bin: EVS_dec
+        ### Decoder output sampling rate; default = null (same as input)
+        # fs: 48000
+################################################
+### Post-processing
+################################################
+### Post-processing step performed after core processing for all conditions
+### Post-processing is required and can not be omitted
+postprocessing:
+    ### REQUIRED: Target format for output
+    fmt: "BINAURAL"
+    ### REQUIRED: Target sampling rate in Hz for resampling
+    fs: 48000
+    ### Linear gain factor to be applied before any other processing
+    gain: 0.316227766
+    ### Low-pass cut-off frequency in Hz; default = null (no filtering)
+    # lp_cutoff: 24000
+    ### Target loudness in LKFS; default = null (no loudness change applied)
+    # loudness: -26
+    ### Spatial audio format in which loudness is adjusted (only used if preprocessing loudness is not null);
+    ### default = null (uses postprocessing fmt if possible)
+    # loudness_fmt: null
+    ### Name of custom binaural dataset (without prefix or suffix);
+    ### default = null (ORANGE53(_Dolby) for BINAURAL, IISofficialMPEG222UC for BINAURAL_ROOM)
+    # bin_dataset: SADIE
+    ### Render LFE to binaural output with the specified gain (only valid for channel-based input); default = null
+    # bin_lfe_gain: 1
+    ### Flag whether output should be limited to avoid clipping (can alter target loudness); default = false
+    limit: true
+    ### Head-tracking trajectory file for binaural output; default = null
+    # trajectory: "path/to/file"
diff --git a/tests/test_processing.py b/tests/test_processing.py
index 0843e03b..1eac22b2 100644
--- a/tests/test_processing.py
+++ b/tests/test_processing.py
@@ -54,12 +54,20 @@ def test_generate_test_items(cfg):
     # read out input path
     config = TestConfig(cfg)
     input_path = Path(config.input_path).resolve().absolute()
+    output_path = Path(config.output_path).resolve().absolute()
+
+    # clean up output directory from last run
+    shutil.rmtree(output_path, ignore_errors=True)
 
     # deduce number of channels based on name
     if "MC" in cfg:
         num_channels = 2  # test stereo
     elif "ISM" in cfg:
         num_channels = 4  # test ISM4
+    elif "OSBA" in cfg:
+        num_channels = 20  # test ISM4SBA3
+    elif "OMASA" in cfg:
+        num_channels = 6  # test ISM4MASA2
     elif "SBA" in cfg:
         num_channels = 4  # test FOA
     elif "MASA" in cfg:
@@ -83,5 +91,18 @@ def test_generate_test_items(cfg):
         .absolute()
     )
     shutil.copy(spectral, input_path.joinpath(spectral.name))
+    if "OMASA" in cfg or "OSBA" in cfg:
+        # copy metadata too
+        ism_metadata = list(Path("./tests/data/ism_metadata").glob("stvISM*.csv"))
+
+        for item in [pink_noise, spectral]:
+            for i, metadata in enumerate(ism_metadata):
+                shutil.copy(metadata, input_path.joinpath(f"{item.name}.{i}.csv"))
+
+            if "OMASA" in cfg:
+                shutil.copy(
+                    "./tests/data/masa_metadata/stv_IVASMASA_2dir2TC.met",
+                    input_path.joinpath(f"{item.name}.met"),
+                )
 
     generate_test(args)
-- 
GitLab


From 014aa40194d7c6d18ebdf12701725c906e403f6c Mon Sep 17 00:00:00 2001
From: Archit Tamarapu <archit.tamarapu@iis.fraunhofer.de>
Date: Tue, 1 Jul 2025 15:37:17 +0200
Subject: [PATCH 3/6] [fix] Broadcasting error in ISM rendering with resampling
 for reference conditions

---
 ivas_processing_scripts/audiotools/convert/objectbased.py | 1 +
 1 file changed, 1 insertion(+)

diff --git a/ivas_processing_scripts/audiotools/convert/objectbased.py b/ivas_processing_scripts/audiotools/convert/objectbased.py
index 16bcc821..b251a28f 100755
--- a/ivas_processing_scripts/audiotools/convert/objectbased.py
+++ b/ivas_processing_scripts/audiotools/convert/objectbased.py
@@ -141,6 +141,7 @@ def render_oba_to_binaural(
 
         # sum results over all objects
         bin.audio = np.sum(np.stack(result, axis=2), axis=2)
+        bin.fs = 48000
 
         # compensate delay from binaural dataset
         bin.audio = delay(bin.audio, bin.fs, -latency_smp, samples=True)
-- 
GitLab


From 15f81eb8b62cac11b9d6bfb9a9e94fe9b409ee42 Mon Sep 17 00:00:00 2001
From: Archit Tamarapu <archit.tamarapu@iis.fraunhofer.de>
Date: Tue, 1 Jul 2025 15:37:52 +0200
Subject: [PATCH 4/6] update TEMPLATE.yml

---
 examples/TEMPLATE.yml | 22 ++++++++++++----------
 1 file changed, 12 insertions(+), 10 deletions(-)

diff --git a/examples/TEMPLATE.yml b/examples/TEMPLATE.yml
index 7c8f99f6..ac00e898 100755
--- a/examples/TEMPLATE.yml
+++ b/examples/TEMPLATE.yml
@@ -178,14 +178,16 @@ input:
 ### List of conditions to generate
 ### Name of the key will be used as output directory name
 ###     conditions must specify the "type" key which may be one of the following options:
-###     ref        generate the reference condition
-###     lp3k5      generate a low-pass anchor with cut-off frequency 3.5 kHz
-###     lp7k       generate a low-pass anchor with cut-off frequency 7 kHz
-###     mnru       generate MNRU condition
-###     esdru      generate ESDRU condition
-###     mono_dmx   generate mono downmix condition
-###     evs        generate an EVS coded condition (see below examples for additional required keys)
-###     ivas       generate an IVAS coded condition (see below examples for additional required keys)
+###     ref             generate the reference condition
+###     lp3k5           generate a low-pass anchor with cut-off frequency 3.5 kHz
+###     lp7k            generate a low-pass anchor with cut-off frequency 7 kHz
+###     mnru            generate MNRU condition
+###     esdru           generate ESDRU condition
+###     mono_dmx        generate mono downmix condition
+###     evs             generate an EVS coded condition (see below examples for additional required keys)
+###     ivas            generate an IVAS coded condition (see below examples for additional required keys)
+###     ivas_combined   generate a combined-format IVAS coded condition using two IVAS instances for each part
+###                     (see below examples for additional required keys)
 conditions_to_generate:
   ### Reference and anchor conditions ##########################
   c01:
@@ -226,7 +228,7 @@ conditions_to_generate:
   c06:
       ### REQUIRED: type of condition
       type: ivas
-      ### REQUIRED: Bitrates to use for coding
+      ### REQUIRED: Bitrates to use for coding, for ivas_combined, first and second bitrates are for objects and spatial parts respectively
       bitrates:
           - 160000
           # - 32000
@@ -264,7 +266,7 @@ conditions_to_generate:
   c07:
       ### REQUIRED: type of condition
       type: ivas
-      ### REQUIRED: Bitrates to use for coding
+      ### REQUIRED: Bitrates to use for coding, for ivas_combined, first and second bitrates are for objects and spatial parts respectively
       bitrates:
           - 160000
           # - 32000
-- 
GitLab


From 1ad9a0516f2a32d652a98881ec1ec13b6016c5e2 Mon Sep 17 00:00:00 2001
From: Archit Tamarapu <archit.tamarapu@iis.fraunhofer.de>
Date: Tue, 15 Jul 2025 12:09:17 +0200
Subject: [PATCH 5/6] formatting

---
 ivas_processing_scripts/processing/ivas_combined.py | 1 -
 1 file changed, 1 deletion(-)

diff --git a/ivas_processing_scripts/processing/ivas_combined.py b/ivas_processing_scripts/processing/ivas_combined.py
index b2caf2b4..6ab83794 100755
--- a/ivas_processing_scripts/processing/ivas_combined.py
+++ b/ivas_processing_scripts/processing/ivas_combined.py
@@ -133,7 +133,6 @@ class IVASCombined(Processing):
     def process(
         self, in_file: Path, out_file: Path, in_meta, logger: logging.Logger
     ) -> None:
-
         logger.debug(f"IVAS configuration : {self.__dict__}")
         logger.debug(f"IVAS {in_file.absolute()} -> {out_file.absolute()}")
 
-- 
GitLab


From 8ce339a5964705eac53c76181fdc4adb5f193722 Mon Sep 17 00:00:00 2001
From: Archit Tamarapu <archit.tamarapu@iis.fraunhofer.de>
Date: Wed, 16 Jul 2025 10:15:15 +0200
Subject: [PATCH 6/6] add 20ch testvectors for ISM4SBA3

---
 tests/data/pinknoise/pink_noise_20ch_48kHz.wav   | 3 +++
 tests/data/spectral/spectral_test_20ch_48kHz.wav | 3 +++
 2 files changed, 6 insertions(+)
 create mode 100644 tests/data/pinknoise/pink_noise_20ch_48kHz.wav
 create mode 100644 tests/data/spectral/spectral_test_20ch_48kHz.wav

diff --git a/tests/data/pinknoise/pink_noise_20ch_48kHz.wav b/tests/data/pinknoise/pink_noise_20ch_48kHz.wav
new file mode 100644
index 00000000..aefe463f
--- /dev/null
+++ b/tests/data/pinknoise/pink_noise_20ch_48kHz.wav
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:412bc5e003fea03f5341d7dd1c4b74ed8f1bced04ac16aec45534f8b39dd1822
+size 1920044
diff --git a/tests/data/spectral/spectral_test_20ch_48kHz.wav b/tests/data/spectral/spectral_test_20ch_48kHz.wav
new file mode 100644
index 00000000..30e98637
--- /dev/null
+++ b/tests/data/spectral/spectral_test_20ch_48kHz.wav
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:39ce9d81bdd6c15196fd6a7e43ae0012a014245f10e66590ebe375ccd0aff6cd
+size 1920044
-- 
GitLab