@inproceedings{wu-etal-2024-codec,
title = "Codec-{SUPERB}: An In-Depth Analysis of Sound Codec Models",
author = "Wu, Haibin and
Chung, Ho-Lam and
Lin, Yi-Cheng and
Wu, Yuan-Kuei and
Chen, Xuanjun and
Pai, Yu-Chi and
Wang, Hsiu-Hsuan and
Chang, Kai-Wei and
Liu, Alexander and
Lee, Hung-yi",
editor = "Ku, Lun-Wei and
Martins, Andre and
Srikumar, Vivek",
booktitle = "Findings of the Association for Computational Linguistics: ACL 2024",
month = aug,
year = "2024",
address = "Bangkok, Thailand",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2024.findings-acl.616/",
doi = "10.18653/v1/2024.findings-acl.616",
pages = "10330--10348",
abstract = "The sound codec`s dual roles in minimizing data transmission latency and serving as tokenizers underscore its critical importance.Recent years have witnessed significant developments in codec models.The ideal sound codec should preserve content, paralinguistics, speakers, and audio information.However, the question of which codec achieves optimal sound information preservation remains unanswered, as in different papers, models are evaluated on their selected experimental settings.This study introduces Codec-SUPERB, an acronym for Codec sound processing Universal PERformance Benchmark.It is an ecosystem designed to assess codec models across representative sound applications and signal-level metrics rooted in sound domain knowledge.Codec-SUPERB simplifies result sharing through an online leaderboard, promoting collaboration within a community-driven benchmark database, thereby stimulating new development cycles for codecs.Furthermore, we undertake an in-depth analysis to offer insights into codec models from both application and signal perspectives, diverging from previous codec papers mainly concentrating on signal-level comparisons.Finally, we will release codes, the leaderboard, and data to accelerate progress within the community."
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="wu-etal-2024-codec">
<titleInfo>
<title>Codec-SUPERB: An In-Depth Analysis of Sound Codec Models</title>
</titleInfo>
<name type="personal">
<namePart type="given">Haibin</namePart>
<namePart type="family">Wu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ho-Lam</namePart>
<namePart type="family">Chung</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yi-Cheng</namePart>
<namePart type="family">Lin</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yuan-Kuei</namePart>
<namePart type="family">Wu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xuanjun</namePart>
<namePart type="family">Chen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yu-Chi</namePart>
<namePart type="family">Pai</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hsiu-Hsuan</namePart>
<namePart type="family">Wang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kai-Wei</namePart>
<namePart type="family">Chang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Alexander</namePart>
<namePart type="family">Liu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hung-yi</namePart>
<namePart type="family">Lee</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2024-08</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Findings of the Association for Computational Linguistics: ACL 2024</title>
</titleInfo>
<name type="personal">
<namePart type="given">Lun-Wei</namePart>
<namePart type="family">Ku</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Andre</namePart>
<namePart type="family">Martins</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Vivek</namePart>
<namePart type="family">Srikumar</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Bangkok, Thailand</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>The sound codec‘s dual roles in minimizing data transmission latency and serving as tokenizers underscore its critical importance.Recent years have witnessed significant developments in codec models.The ideal sound codec should preserve content, paralinguistics, speakers, and audio information.However, the question of which codec achieves optimal sound information preservation remains unanswered, as in different papers, models are evaluated on their selected experimental settings.This study introduces Codec-SUPERB, an acronym for Codec sound processing Universal PERformance Benchmark.It is an ecosystem designed to assess codec models across representative sound applications and signal-level metrics rooted in sound domain knowledge.Codec-SUPERB simplifies result sharing through an online leaderboard, promoting collaboration within a community-driven benchmark database, thereby stimulating new development cycles for codecs.Furthermore, we undertake an in-depth analysis to offer insights into codec models from both application and signal perspectives, diverging from previous codec papers mainly concentrating on signal-level comparisons.Finally, we will release codes, the leaderboard, and data to accelerate progress within the community.</abstract>
<identifier type="citekey">wu-etal-2024-codec</identifier>
<identifier type="doi">10.18653/v1/2024.findings-acl.616</identifier>
<location>
<url>https://aclanthology.org/2024.findings-acl.616/</url>
</location>
<part>
<date>2024-08</date>
<extent unit="page">
<start>10330</start>
<end>10348</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Codec-SUPERB: An In-Depth Analysis of Sound Codec Models
%A Wu, Haibin
%A Chung, Ho-Lam
%A Lin, Yi-Cheng
%A Wu, Yuan-Kuei
%A Chen, Xuanjun
%A Pai, Yu-Chi
%A Wang, Hsiu-Hsuan
%A Chang, Kai-Wei
%A Liu, Alexander
%A Lee, Hung-yi
%Y Ku, Lun-Wei
%Y Martins, Andre
%Y Srikumar, Vivek
%S Findings of the Association for Computational Linguistics: ACL 2024
%D 2024
%8 August
%I Association for Computational Linguistics
%C Bangkok, Thailand
%F wu-etal-2024-codec
%X The sound codec‘s dual roles in minimizing data transmission latency and serving as tokenizers underscore its critical importance.Recent years have witnessed significant developments in codec models.The ideal sound codec should preserve content, paralinguistics, speakers, and audio information.However, the question of which codec achieves optimal sound information preservation remains unanswered, as in different papers, models are evaluated on their selected experimental settings.This study introduces Codec-SUPERB, an acronym for Codec sound processing Universal PERformance Benchmark.It is an ecosystem designed to assess codec models across representative sound applications and signal-level metrics rooted in sound domain knowledge.Codec-SUPERB simplifies result sharing through an online leaderboard, promoting collaboration within a community-driven benchmark database, thereby stimulating new development cycles for codecs.Furthermore, we undertake an in-depth analysis to offer insights into codec models from both application and signal perspectives, diverging from previous codec papers mainly concentrating on signal-level comparisons.Finally, we will release codes, the leaderboard, and data to accelerate progress within the community.
%R 10.18653/v1/2024.findings-acl.616
%U https://aclanthology.org/2024.findings-acl.616/
%U https://doi.org/10.18653/v1/2024.findings-acl.616
%P 10330-10348
Markdown (Informal)
[Codec-SUPERB: An In-Depth Analysis of Sound Codec Models](https://aclanthology.org/2024.findings-acl.616/) (Wu et al., Findings 2024)
ACL
- Haibin Wu, Ho-Lam Chung, Yi-Cheng Lin, Yuan-Kuei Wu, Xuanjun Chen, Yu-Chi Pai, Hsiu-Hsuan Wang, Kai-Wei Chang, Alexander Liu, and Hung-yi Lee. 2024. Codec-SUPERB: An In-Depth Analysis of Sound Codec Models. In Findings of the Association for Computational Linguistics: ACL 2024, pages 10330–10348, Bangkok, Thailand. Association for Computational Linguistics.