From 2ce8202f1ea141f7378e88582e51d43da0e6dd7e Mon Sep 17 00:00:00 2001 From: vaclav Date: Mon, 6 Mar 2023 09:01:47 +0100 Subject: [PATCH] updates/corrections wrt. self-test vectors and readme.txt --- readme.txt | 105 ++++++++++-------- scripts/config/self_test.prm | 16 +-- ...g => rend_config_hospital_patientroom.cfg} | 0 ...reation.cfg => rend_config_recreation.cfg} | 0 ..._renderer.cfg => rend_config_renderer.cfg} | 0 5 files changed, 69 insertions(+), 52 deletions(-) rename scripts/testv/{config_hospital_patientroom.cfg => rend_config_hospital_patientroom.cfg} (100%) rename scripts/testv/{config_recreation.cfg => rend_config_recreation.cfg} (100%) rename scripts/testv/{config_renderer.cfg => rend_config_renderer.cfg} (100%) diff --git a/readme.txt b/readme.txt index 649fe1c4cd..eeaea0f84a 100644 --- a/readme.txt +++ b/readme.txt @@ -296,6 +296,7 @@ The output channel ordering is 0, 1, ... N-1. The third row contains an index "L specifying the output channel to which the LFE input will be routed if present. If the third row is omitted, the LFE input is downmixed to all channels with a factor of 1/N. Position is not considered for the LFE channel. +An example custom loudspeaker layout file is available: ls_setup_16ch_8+4+4.txt @@ -310,55 +311,56 @@ points or complete coverage. Documentation on the self_test.py can be found as a part of scripts/README.md. -Note: Running the self_test.py requires the input vectors in the folder scripts/testv. The -audio files could unfortunately not be shared, and they need to be replaced in order to -run the self_test.py. To complement the test vector set, please replace the empty *.pcm-files -in the self_test folder with 16 bit PCM files following the specification below. - -stv1ISM48s.pcm - 1 channel (1 audio object), 48000 Hz, 1440000 samples -stv2ISM48s.pcm - 2 channels (discrete audio objects), 48000 Hz, 1440000 samples per channel -stv2OA32c.pcm - 9 channels (2nd order Ambisonics ACN/SN3D), 32000 Hz -stv2OA48c.pcm - 9 channels (2nd order Ambisonics ACN/SN3D), 48000 Hz -stv3ISM48s.pcm - 3 channels (discrete audio objects), 48000 Hz, 1440000 samples per channel -stv3OA32c.pcm - 16 channels (3rd order Ambisonics ACN/SN3D), 32000 Hz, 288939 samples per channel -stv3OA48c.pcm - 16 channels (3rd order Ambisonics ACN/SN3D), 48000 Hz, 433408 samples per channel -stv4ISM48s.pcm - 4 channel (discrete audio objects), 48000 Hz, 1440000 samples per channel -stv8c.pcm - 1 channel, 8000 Hz, clean speech/audio -stv8n.pcm - 1 channel, 8000 Hz, noisy speech -stv16c.pcm - 1 channel, 16000 Hz, 610307 samples, clean speech -stv16n.pcm - 1 channel, 16000 Hz, 257024 samples, noisy speech -stv32c.pcm - 1 channel, 32000 Hz, 1220613 samples, clean speech/audio -stv32n.pcm - 1 channel, 32000 Hz, 514048 samples, noisy speech -stv48c.pcm - 1 channel, 48000 Hz, 1830919 samples, clean speech/audio -stv51MC48c.pcm - 6 channels (5.1 1..6 where 4th channel is LFE), 3231233 samples per channel, 48000 Hz, movie excerpt -stv512MC48c.pcm - 8 channels (5.1+2 1..8 where 4th channel is LFE), 144000 samples per channel, 48000 Hz, movie excerpt -stv714MC48c.pcm - 12 channels (7.1+4 1..12 where 4th channel is LFE), 144000 samples per channel, 48000 Hz, movie excerpt -stvFOA16c.pcm - 4 channels (1st order Ambisonics ACN/SN3D), 16000 Hz, -stvFOA32c.pcm - 4 channels (1st order Ambisonics ACN/SN3D), 32000 Hz, 288939 samples per channel -stvFOA48c.pcm - 4 channels (1st order Ambisonics ACN/SN3D), 48000 Hz, 433408 samples per channel -stvST16c.pcm - 2 channels, 16000 Hz, 329601 samples per channel, clean speech/audio -stvST16n.pcm - 2 channels, 16000 Hz, 310401 samples per channel, noisy speech -stvST32c.pcm - 2 channels, 32000 Hz, 659200 samples per channel, clean speech/audio -stvST32n.pcm - 2 channels, 32000 Hz, 620800 samples per channel, noisy speech -stvST48c.pcm - 2 channels, 48000 Hz, 988800 samples per channel, clean speech/audio -stvST48n.pcm - 2 channels, 48000 Hz, 931200 samples per channel, noisy speech -stv_IVASMASA_1dir1TC.pcm - 1 channel (1 MASA transport channel), 48000 Hz, 48000 Hz, 144000 samples -stv_IVASMASA_1dir1TC_DTX.pcm - 1 channel (1 MASA transport channel), 48000 Hz, 48000 Hz, 963840 samples -stv_IVASMASA_1dir2TC.pcm - 2 channels (2 MASA transport channel), 48000 Hz, 48000 Hz, 288000 samples per channel -stv_IVASMASA_1dir2TC_DTX.pcm - 2 channels (2 MASA transport channel), 48000 Hz, 48000 Hz, 963840 samples per channel -stv_IVASMASA_2dir1TC.pcm - 1 channel (1 MASA transport channel), 48000 Hz, 48000 Hz, 288000 -stv_IVASMASA_2dir2TC.pcm - 2 channels (2 MASA transport channel), 48000 Hz, 48000 Hz, 144000 samples per channel +Note: Running the self_test.py requires the input vectors in the folder scripts/testv. + +stv1ISM48s.wav - 1 channel (1 audio object), 48000 Hz, 1440000 samples +stv2ISM48s.wav - 2 channels (discrete audio objects), 48000 Hz, 1440000 samples per channel +stv2OA32c.wav - 9 channels (2nd order Ambisonics ACN/SN3D), 32000 Hz +stv2OA48c.wav - 9 channels (2nd order Ambisonics ACN/SN3D), 48000 Hz +stv3ISM48s.wav - 3 channels (discrete audio objects), 48000 Hz, 1440000 samples per channel +stv3OA32c.wav - 16 channels (3rd order Ambisonics ACN/SN3D), 32000 Hz, 288939 samples per channel +stv3OA48c.wav - 16 channels (3rd order Ambisonics ACN/SN3D), 48000 Hz, 433408 samples per channel +stv4ISM48s.wav - 4 channel (discrete audio objects), 48000 Hz, 1440000 samples per channel +stv4ISM48n.wav - 4 channel (discrete audio objects), 48000 Hz, noisy speech +stv8c.wav - 1 channel, 8000 Hz, clean speech/audio +stv8n.wav - 1 channel, 8000 Hz, noisy speech +stv16c.wav - 1 channel, 16000 Hz, 610307 samples, clean speech +stv16n.wav - 1 channel, 16000 Hz, 257024 samples, noisy speech +stv32c.wav - 1 channel, 32000 Hz, 1220613 samples, clean speech/audio +stv32n.wav - 1 channel, 32000 Hz, 514048 samples, noisy speech +stv48c.wav - 1 channel, 48000 Hz, 960000 samples, clean speech/audio +stv48n.wav - 1 channel, 48000 Hz, 931200 samples, noisy clean speech +stv51MC48c.wav - 6 channels (5.1 1..6 where 4th channel is LFE), 960000 samples per channel, 48000 Hz +stv512MC48c.wav - 8 channels (5.1+2 1..8 where 4th channel is LFE), 144000 samples per channel, 48000 Hz +stv514MC48c.wav - 10 channels (7.1+2 1..10 where 4th channel is LFE), 144000 samples per channel, 48000 Hz +stv71MC48c.wav - 8 channels (7.1 1..8 where 4th channel is LFE), 144000 samples per channel, 48000 Hz +stv714MC48c.wav - 12 channels (7.1+4 1..12 where 4th channel is LFE), 144000 samples per channel, 48000 Hz +stvFOA16c.wav - 4 channels (1st order Ambisonics ACN/SN3D), 16000 Hz, +stvFOA32c.wav - 4 channels (1st order Ambisonics ACN/SN3D), 32000 Hz, 288939 samples per channel +stvFOA48c.wav - 4 channels (1st order Ambisonics ACN/SN3D), 48000 Hz, 433408 samples per channel +stvST16c.wav - 2 channels, 16000 Hz, 329601 samples per channel, clean speech/audio +stvST16n.wav - 2 channels, 16000 Hz, 310401 samples per channel, noisy speech +stvST32c.wav - 2 channels, 32000 Hz, 659200 samples per channel, clean speech/audio +stvST32n.wav - 2 channels, 32000 Hz, 620800 samples per channel, noisy speech +stvST48c.wav - 2 channels, 48000 Hz, 988800 samples per channel, clean speech/audio +stvST48n.wav - 2 channels, 48000 Hz, 931200 samples per channel, noisy speech +stv1MASA1TC48c.wav - 1 channel (1 MASA transport channel), 48000 Hz, 48000 Hz, 144000 samples +stv1MASA1TC48n.wav - 1 channel (1 MASA transport channel), 48000 Hz, 48000 Hz, 963840 samples +stv1MASA2TC48c.wav - 2 channels (2 MASA transport channel), 48000 Hz, 48000 Hz, 288000 samples per channel +stv1MASA2TC48n.wav - 2 channels (2 MASA transport channel), 48000 Hz, 48000 Hz, 963840 samples per channel +stv2MASA1TC48c.wav - 1 channel (1 MASA transport channel), 48000 Hz, 48000 Hz, 288000 +stv2MASA2TC48c.wav - 2 channels (2 MASA transport channel), 48000 Hz, 48000 Hz, 144000 samples per channel For the MASA operation modes, in addition the following metadata files are required: -stv_IVASMASA_1dir1TC.met -stv_IVASMASA_1dir1TC_DTX.met -stv_IVASMASA_1dir2TC.met -stv_IVASMASA_1dir2TC_DTX.met -stv_IVASMASA_2dir1TC.met -stv_IVASMASA_2dir2TC.met +stv1MASA1TC48c.met +stv1MASA1TC48n.met +stv1MASA2TC48c.met +stv1MASA2TC48n.met +stv2MASA1TC48c.met +stv2MASA2TC48c.met It is strongly recommended to align these files to the corresponding PCM audio files. The MASA metadata files can be generated with the @@ -393,6 +395,21 @@ with the following meaning: ----------------------------------------------------------------------------------- +For the Head rotation operation modes, external trajectory files are available: + +headrot.csv +headrot_case00_3000_q.csv +headrot_case01_3000_q.csv +headrot_case02_3000_q.csv +headrot_case03_3000_q.csv + + +For the Renderer configuration option operation modes, external configuration files are available: + +rend_config_hospital_patientroom.cfg +config_recreation.cfg +config_renderer.cfg + ADDITIONAL SCRIPTS ================== diff --git a/scripts/config/self_test.prm b/scripts/config/self_test.prm index 7f48f1a1cf..4a925bd693 100644 --- a/scripts/config/self_test.prm +++ b/scripts/config/self_test.prm @@ -863,35 +863,35 @@ // Multi-channel 5_1 at 512 kbps, 48kHz in, 48kHz out, BINAURAL_ROOM out Config renderer ../IVAS_cod -mc 5_1 512000 48 testv/stv51MC48c.wav bit -../IVAS_dec -render_config testv/config_renderer.cfg BINAURAL_ROOM 48 bit testv/stv51MC48c.wav_MC51_512000_48-48_MC_Config_renderer.tst +../IVAS_dec -render_config testv/rend_config_renderer.cfg BINAURAL_ROOM 48 bit testv/stv51MC48c.wav_MC51_512000_48-48_MC_Config_renderer.tst // Multi-channel 5_1 at 512 kbps, 48kHz in, 32kHz out, BINAURAL_ROOM out Config renderer ../IVAS_cod -mc 5_1 512000 48 testv/stv51MC48c.wav bit -../IVAS_dec -render_config testv/config_renderer.cfg BINAURAL_ROOM 32 bit testv/stv51MC48c.wav_MC51_512000_48-32_MC_Config_renderer.tst +../IVAS_dec -render_config testv/rend_config_renderer.cfg BINAURAL_ROOM 32 bit testv/stv51MC48c.wav_MC51_512000_48-32_MC_Config_renderer.tst // Multi-channel 5_1 at 512 kbps, 48kHz in, 16kHz out, BINAURAL_ROOM out Config renderer ../IVAS_cod -mc 5_1 512000 48 testv/stv51MC48c.wav bit -../IVAS_dec -render_config testv/config_renderer.cfg BINAURAL_ROOM 16 bit testv/stv51MC48c.wav_MC51_512000_48-16_MC_Config_renderer.tst +../IVAS_dec -render_config testv/rend_config_renderer.cfg BINAURAL_ROOM 16 bit testv/stv51MC48c.wav_MC51_512000_48-16_MC_Config_renderer.tst // Multi-channel 5_1 at 512 kbps, 48kHz in, 48kHz out, BINAURAL_ROOM out Config hospital_patientroom ../IVAS_cod -mc 5_1 512000 48 testv/stv51MC48c.wav bit -../IVAS_dec -render_config testv/config_hospital_patientroom.cfg BINAURAL_ROOM 48 bit testv/stv51MC48c.wav_MC51_512000_48-48_MC_Config_hospital_patientroom.tst +../IVAS_dec -render_config testv/rend_config_hospital_patientroom.cfg BINAURAL_ROOM 48 bit testv/stv51MC48c.wav_MC51_512000_48-48_MC_Config_hospital_patientroom.tst // Multi-channel 5_1 at 512 kbps, 48kHz in, 48kHz out, BINAURAL_ROOM out Config recreation ../IVAS_cod -mc 5_1 512000 48 testv/stv51MC48c.wav bit -../IVAS_dec -render_config testv/config_recreation.cfg BINAURAL_ROOM 48 bit testv/stv51MC48c.wav_MC51_512000_48-48_MC_Config_recreation.tst +../IVAS_dec -render_config testv/rend_config_recreation.cfg BINAURAL_ROOM 48 bit testv/stv51MC48c.wav_MC51_512000_48-48_MC_Config_recreation.tst // Multi-channel 5_1_2 at 512 kbps, 48kHz in, 48kHz out, BINAURAL_ROOM out Config renderer ../IVAS_cod -mc 5_1_2 512000 48 testv/stv512MC48c.wav bit -../IVAS_dec -render_config testv/config_renderer.cfg BINAURAL_ROOM 48 bit testv/stv512MC48c.wav_MC512_512000_48-48_MC_Config_renderer.tst +../IVAS_dec -render_config testv/rend_config_renderer.cfg BINAURAL_ROOM 48 bit testv/stv512MC48c.wav_MC512_512000_48-48_MC_Config_renderer.tst // Multi-channel 5_1_4 at 512 kbps, 48kHz in, 48kHz out, BINAURAL_ROOM out Config renderer ../IVAS_cod -mc 5_1_4 512000 48 testv/stv514MC48c.wav bit -../IVAS_dec -render_config testv/config_renderer.cfg BINAURAL_ROOM 48 bit testv/stv514MC48c.wav_MC514_512000_48-48_MC_Config_renderer.tst +../IVAS_dec -render_config testv/rend_config_renderer.cfg BINAURAL_ROOM 48 bit testv/stv514MC48c.wav_MC514_512000_48-48_MC_Config_renderer.tst // Multi-channel 7_1_4 at 512 kbps, 48kHz in, 48kHz out, BINAURAL_ROOM out Config renderer ../IVAS_cod -mc 7_1_4 512000 48 testv/stv714MC48c.wav bit -../IVAS_dec -render_config testv/config_renderer.cfg BINAURAL_ROOM 48 bit testv/stv714MC48c.wav_MC714_512000_48-48_MC_Config_renderer.tst +../IVAS_dec -render_config testv/rend_config_renderer.cfg BINAURAL_ROOM 48 bit testv/stv714MC48c.wav_MC714_512000_48-48_MC_Config_renderer.tst // Multi-channel 5_1 bitrate switching from 13.2 kbps to 512 kbps, 48kHz in, 48kHz out, 7_1_4 out ../IVAS_cod -mc 5_1 ../scripts/switchPaths/sw_mctech_5fr.bin 48 testv/stv51MC48c.wav bit diff --git a/scripts/testv/config_hospital_patientroom.cfg b/scripts/testv/rend_config_hospital_patientroom.cfg similarity index 100% rename from scripts/testv/config_hospital_patientroom.cfg rename to scripts/testv/rend_config_hospital_patientroom.cfg diff --git a/scripts/testv/config_recreation.cfg b/scripts/testv/rend_config_recreation.cfg similarity index 100% rename from scripts/testv/config_recreation.cfg rename to scripts/testv/rend_config_recreation.cfg diff --git a/scripts/testv/config_renderer.cfg b/scripts/testv/rend_config_renderer.cfg similarity index 100% rename from scripts/testv/config_renderer.cfg rename to scripts/testv/rend_config_renderer.cfg -- GitLab