Commit 41a6e390 authored by Archit Tamarapu's avatar Archit Tamarapu
Browse files

add option for linear gain factor in audiotools and processing scripts

parent 4b5defdf

examples/TEMPLATE.yml

+4 −0
Original line number Diff line number Diff line
@@ -77,6 +77,8 @@ input: 
### 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
@@ -319,6 +321,8 @@ postprocessing: 
    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)

ivas_processing_scripts/audiotools/__init__.py

+7 −0
Original line number Diff line number Diff line
@@ -114,6 +114,13 @@ def add_processing_args(group, input=True): 
        help="Delay the signal by this amount in milliseconds (negative values advance, default = %(default)s)",

        default=None,

    )

    group.add_argument(

        f"-{ps}g",

        f"--{p}_gain",

        type=float,

        help="Apply the given linear gain factor to the signal, applied before other processing steps (default = %(default)s)",

        default=None,

    )

    group.add_argument(

        f"-{ps}l",

        f"--{p}_loudness",

ivas_processing_scripts/audiotools/convert/__init__.py

+11 −0
Original line number Diff line number Diff line
@@ -190,6 +190,7 @@ def convert( 
    in_cutoff: Optional[int] = None,

    in_mask: Optional[str] = None,

    in_window: Optional[list] = None,

    in_gain: Optional[float] = None,

    in_loudness: Optional[float] = None,

    in_loudness_fmt: Optional[str] = None,

    out_trim: Optional[list] = None,
@@ -199,6 +200,7 @@ def convert( 
    out_cutoff: Optional[int] = None,

    out_mask: Optional[str] = None,

    out_window: Optional[list] = None,

    out_gain: Optional[float] = None,

    out_loudness: Optional[float] = None,

    out_loudness_fmt: Optional[str] = None,

    limit: Optional[bool] = False,
@@ -221,6 +223,7 @@ def convert( 
        fc=in_cutoff,

        mask=in_mask,

        window=in_window,

        gain=in_gain,

        loudness=in_loudness,

        loudness_fmt=in_loudness_fmt,

        spatial_distortion_amplitude=spatial_distortion_amplitude,
@@ -241,6 +244,7 @@ def convert( 
        fc=out_cutoff,

        mask=out_mask,

        window=out_window,

        gain=out_gain,

        loudness=out_loudness,

        loudness_fmt=out_loudness_fmt,

        limit=limit,
@@ -259,6 +263,7 @@ def process_audio( 
    fc: Optional[int] = None,

    mask: Optional[str] = None,

    window: Optional[float] = None,

    gain: Optional[float] = None,

    loudness: Optional[float] = None,

    loudness_fmt: Optional[str] = None,

    limit: Optional[bool] = False,
@@ -273,6 +278,12 @@ def process_audio( 
    if fs is None:

        fs = x.fs



    """gain"""

    if gain is not None:

        if logger:

            logger.debug(f"Applying linear gain factor of {gain}")

        x.audio *= gain



    """delay audio"""

    if delay is not None:

        if isinstance(x, audio.ObjectBasedAudio):

ivas_processing_scripts/bin/README.md

+15 −15
Original line number Diff line number Diff line 


Necessary additional executables:



| Processing step                                 | Executable            | Where to find                                                                                               |

| ------------------------------------------------------------------------------------------- | --------------------- | --------------------------------------------------------------------------------------------------------------- |

| Loudness measurement and adjustment                                                         | bs1770demo            | <https://github.com/ErikNorvell-Ericsson/STL> (Note branch)                                                     |

| MNRU                                                                                        | p50fbmnru             | <https://github.com/openitu/STL>                                                                                |

| ESDRU                                                                                       | esdru                 | <https://github.com/openitu/STL>                                                                                |

| Frame error pattern application                                                             | eid-xor               | <https://github.com/openitu/STL>                                                                                |

| Reverberation module                                                                        | reverb                | <https://github.com/openitu/STL>                                                                                |

| Error pattern generation                                                                    | gen-patt              | <https://www.itu.int/rec/T-REC-G.191-201003-S/en> (Note: Version in <https://github.com/openitu/STL> is buggy!) |

| Filtering, Resampling                                                                       | filter                | <https://www.3gpp.org/ftp/tsg_sa/WG4_CODEC/TSGS4_76/docs/S4-131277.zip>                                         |

| Random offset/seed generation (necessary for background noise and FER bitstream processing) | random                | <https://www.3gpp.org/ftp/tsg_sa/WG4_CODEC/TSGS4_76/docs/S4-131277.zip>                                         |

| JBM network simulator                                                                       | networkSimulator_g192 | <https://www.3gpp.org/ftp/tsg_sa/WG4_CODEC/TSGS4_76/docs/S4-131277.zip>                                         |

| MASA analyzer (used for SBA to MASA conversion)                                             | masaRenderer          | <https://www.3gpp.org/ftp/TSG_SA/WG4_CODEC/TSGS4_122_Athens/Docs/S4-230221.zip>                                 |

| MASA rendering (also used in loudness measurement of MASA items)                            | masaAnalyzer          | <https://www.3gpp.org/ftp/TSG_SA/WG4_CODEC/TSGS4_122_Athens/Docs/S4-230221.zip>                                 |

| EVS reference conditions                                                                    | EVS_cod, EVS_dec      | <https://www.3gpp.org/ftp/Specs/archive/26_series/26.443/26443-h00.zip>                                         |

| EVS JBM conditions                                                                          | dlyerr_2_errpat       | <http://ftp.3gpp.org/tsg_sa/WG4_CODEC/TSGS4_70/Docs/S4-121077.zip>                                              |
 
|-------------------------------------------------|-----------------------|-------------------------------------------------------------------------------------------------------------|

| Loudness measurement and adjustment             | bs1770demo            | https://github.com/ErikNorvell-Ericsson/STL (Note branch)                                                   |

| MNRU                                            | p50fbmnru             | https://github.com/openitu/STL                                                                              |

| ESDRU                                           | esdru                 | https://github.com/openitu/STL                                                                              |

| Frame error pattern application                 | eid-xor               | https://github.com/openitu/STL                                                                              |

| Reverberation module                            | reverb                | https://github.com/openitu/STL                                                                              |

| Error pattern generation                        | gen-patt              | https://www.itu.int/rec/T-REC-G.191-201003-S/en (Note: Version in https://github.com/openitu/STL is buggy!) |

| Filtering, Resampling                           | filter                | https://www.3gpp.org/ftp/tsg_sa/WG4_CODEC/TSGS4_76/docs/S4-131277.zip                                       |

| Random offset/seed generation (necessary for background noise and FER bitstream processing)   | random                | https://www.3gpp.org/ftp/tsg_sa/WG4_CODEC/TSGS4_76/docs/S4-131277.zip                                       |

| JBM network simulator                           | networkSimulator_g192 | https://www.3gpp.org/ftp/tsg_sa/WG4_CODEC/TSGS4_76/docs/S4-131277.zip                                       |

| MASA rendering (also used in loudness measurement of MASA items)        | masaRenderer        | https://www.3gpp.org/ftp/TSG_SA/WG4_CODEC/TSGS4_122_Athens/Docs/S4-230221.zip                               |

| EVS reference conditions        | EVS_cod, EVS_dec      | https://www.3gpp.org/ftp/Specs/archive/26_series/26.443/26443-h00.zip                                       |

| EVS JBM conditions | dlyerr_2_errpat | http://ftp.3gpp.org/tsg_sa/WG4_CODEC/TSGS4_70/Docs/S4-121077.zip |
 
 No newline at end of file

ivas_processing_scripts/processing/chains.py

+2 −0
Original line number Diff line number Diff line
@@ -137,6 +137,7 @@ def get_preprocessing(cfg: TestConfig) -> dict: 
                "in_pad_noise": pre_cfg.get("pad_noise", False),

                "in_delay": pre_cfg.get("delay"),

                "in_window": pre_cfg.get("window"),

                "in_gain": pre_cfg.get("gain"),

                "in_loudness": pre_cfg.get("loudness"),

                "in_loudness_fmt": pre_cfg.get("loudness_fmt", post_fmt),

                "in_mask": pre_cfg.get("mask", None),
@@ -568,6 +569,7 @@ def get_processing_chain( 
                "out_fs": post_cfg.get("fs"),

                "out_fmt": post_fmt,

                "out_cutoff": tmp_lp_cutoff,

                "in_gain": post_cfg.get("gain"), # should be in_gain here since we want to apply it before any conversion/rendering

                "bin_dataset": post_cfg.get("bin_dataset"),

                "bin_lfe_gain": post_cfg.get("bin_lfe_gain"),

                "limit": post_cfg.get("limit", True),