Commit 64331e98 authored by Jan Kiene's avatar Jan Kiene
Browse files

Merge branch '28-masa-selection-test-experiments' of... 

Merge branch '28-masa-selection-test-experiments' of forge.3gpp.org:ivas-codec-pc/ivas-processing-scripts into masa_selection_tests
parents 9b06fe60 6609487a

.gitignore

+0 −1
Original line number Diff line number Diff line
@@ -6,7 +6,6 @@ venv/ 
.vscode/

.idea/

.DS_Store

*.wav

!tests/data/**/*.wav

*.pcm

*.bs

.gitlab-ci.yml

+8 −3
Original line number Diff line number Diff line
@@ -24,10 +24,10 @@ stages: 


# print some info on the runner setup

.print-common-info: &print-common-info

  - echo "--------------------------------------------\n"

  - echo "--------------------------------------------"

  - python3 --version

  - pip3 freeze | grep "numpy\|scipy\|YAML\|pytest\|black\|isort\|flake8"

  - echo "--------------------------------------------\n\n"

  - echo "--------------------------------------------"





# script anchor for updating the codec repo
@@ -36,7 +36,12 @@ stages: 
  # NOTE: CODEC_DIR has to be in PATH

  - cd $CODEC_DIR

  # make sure that we are at latest main

  - git pull

  # TODO: temporarily use the RC1a tag

  - git restore .

  - git checkout 20230511-RC1a-listening-tests

  - echo "--------------------------------------------"

  - echo "Building codec on commit $(git rev-parse HEAD --short)"

  - echo "--------------------------------------------"

  # only builds if code has actually changed

  - make -j

  - cd $dir

README.md

+3 −3
Original line number Diff line number Diff line
@@ -202,7 +202,7 @@ input: 
    ### 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)

    ### default = null (uses postprocessing fmt)

    # loudness_fmt: "BINAURAL"

    ### Pre-/post-trim individual signal(s) (ms) (negative values pad silence); default = 0

    # trim:
@@ -400,7 +400,7 @@ conditions_to_generate: 
          ### Decoder output sampling rate; default = null (same as input)

          # fs: 48000

	  ### Option to use SBA format of lower or same order (planar also possible) for SBA input formats

      # sba_format: "PLANARFOA"

      # sba_fmt: "PLANARFOA"

```



</details>
@@ -474,7 +474,7 @@ For the encoding stage `cod` and the decoding stage `dec`, the path to the IVAS_ 
Additionally some resampling can be applied by using the key `fs` followed by the desired sampling rate.

The general bitstream processing configuration can be locally overwritten for each EVS and IVAS condition with the key `tx`.

The additional key `evs_lfe_9k6bps_nb` is only available for EVS conditions and ensures a bitrate of 9.6kbps and narrow band processing of the LFE channel(s).

Also only available for EVS conditions is the `sba_format` key where a SBA format of lower order than the input can be specified for SBA input formats.

Also only available for EVS conditions is the `sba_fmt` key where a SBA format of lower order than the input can be specified for SBA input formats.

#### IVAS

The configuration of the IVAS condition is similar to the EVS condition. However, only one bitrate for all channels (and metadata) can be specified.

In addition to that, the encoder and decoder take some additional arguments defined by the key `opts`.

examples/TEMPLATE.yml

+6 −2
Original line number Diff line number Diff line
@@ -49,6 +49,10 @@ output_path: ".../tmp_output" 
# input_select:

#  - "48kHz"



### Include the condition number in the item name; default = false

### for e.g. abcxyz.wav --> abcxyz.cXX.wav

# condition_in_output_filename: true



################################################

### Input configuration

################################################
@@ -73,7 +77,7 @@ input: 
    ### 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)

    ### default = null (uses postprocessing fmt)

    # loudness_fmt: "BINAURAL"

    ### Pre-/post-trim individual signal(s) (ms) (negative values pad silence); default = 0

    # trim:
@@ -266,7 +270,7 @@ conditions_to_generate: 
      # tx:

          ### For possible arguments see overall bitstream modification

      ### Option to use SBA format of lower or same order (planar also possible) for SBA input formats

      # sba_format: "PLANARFOA"

      # sba_fmt: "PLANARFOA"



################################################

### Post-processing

experiments/selection/BS1534-4a/config/BS1534-4a.yml

+3 −3
Original line number Diff line number Diff line
@@ -51,26 +51,26 @@ conditions_to_generate: 
    ### EVS condition ################################

    c03:

        type: evs

        sba_fmt: "FOA"

        bitrates:

            - 24400

        cod:

            fmt: "FOA"

            opts: ["-max_band", "FB"]

        dec:

    c04:

        type: evs

        sba_fmt: "FOA"

        bitrates:

            - 32000

        cod:

            fmt: "FOA"

            opts: ["-max_band", "FB"]

        dec:

    c05:

        type: evs

        sba_fmt: "FOA"

        bitrates:

            - 48000

        cod:

            fmt: "FOA"

            opts: ["-max_band", "FB"]

        dec: