{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,4]],"date-time":"2026-06-04T15:36:20Z","timestamp":1780587380631,"version":"3.54.1"},"reference-count":53,"publisher":"IEEE","license":[{"start":{"date-parts":[[2024,12,2]],"date-time":"2024-12-02T00:00:00Z","timestamp":1733097600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,12,2]],"date-time":"2024-12-02T00:00:00Z","timestamp":1733097600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2024,12,2]]},"DOI":"10.1109\/slt61566.2024.10832364","type":"proceedings-article","created":{"date-parts":[[2025,1,16]],"date-time":"2025-01-16T18:31:27Z","timestamp":1737052287000},"page":"570-577","source":"Crossref","is-referenced-by-count":9,"title":["Codec-Superb @ SLT 2024: A Lightweight Benchmark For Neural Audio Codec Models"],"prefix":"10.1109","author":[{"given":"Haibin","family":"Wu","sequence":"first","affiliation":[{"name":"National Taiwan University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xuanjun","family":"Chen","sequence":"additional","affiliation":[{"name":"National Taiwan University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yi-Cheng","family":"Lin","sequence":"additional","affiliation":[{"name":"National Taiwan University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Kaiwei","family":"Chang","sequence":"additional","affiliation":[{"name":"National Taiwan University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jiawei","family":"Du","sequence":"additional","affiliation":[{"name":"National Taiwan University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ke-Han","family":"Lu","sequence":"additional","affiliation":[{"name":"National Taiwan University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Alexander H.","family":"Liu","sequence":"additional","affiliation":[{"name":"Massachusetts Institute of Technology"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ho-Lam","family":"Chung","sequence":"additional","affiliation":[{"name":"National Taiwan University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yuan-Kuei","family":"Wu","sequence":"additional","affiliation":[{"name":"National Taiwan University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Dongchao","family":"Yang","sequence":"additional","affiliation":[{"name":"The Chinese University of Hong Kong"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Songxiang","family":"Liu","sequence":"additional","affiliation":[{"name":"The Chinese University of Hong Kong"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yi-Chiao","family":"Wu","sequence":"additional","affiliation":[{"name":"Meta"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xu","family":"Tan","sequence":"additional","affiliation":[{"name":"Microsoft Corporation"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"James","family":"Glass","sequence":"additional","affiliation":[{"name":"Massachusetts Institute of Technology"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Shinji","family":"Watanabe","sequence":"additional","affiliation":[{"name":"Carnegie Mellon University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hung-Yi","family":"Lee","sequence":"additional","affiliation":[{"name":"National Taiwan University"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","article-title":"Principles of digital audio","author":"Ken","year":"2000"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2023.3288409"},{"key":"ref3","article-title":"Neural codec language models are zero-shot text to speech synthesizers","author":"Wang","year":"2023","journal-title":"arXiv preprint arXiv:2301.02111"},{"key":"ref4","article-title":"Audiogen: Textually guided audio generation","author":"Kreuk","year":"2022","journal-title":"arXiv preprint arXiv:2209.15352"},{"key":"ref5","article-title":"Musiclm: Generating music from text","author":"Agostinelli","year":"2023","journal-title":"arXiv preprint arXiv:2301.11325"},{"key":"ref6","article-title":"Towards audio language modeling-an overview","author":"Wu","year":"2024","journal-title":"arXiv preprint arXiv:2402.13236"},{"key":"ref7","article-title":"High fidelity neural audio compression","author":"D\u00e9fossez","year":"2022","journal-title":"arXiv preprint arXiv:2210.13438"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3129994"},{"key":"ref9","article-title":"Sound-storm: Efficient parallel audio generation","author":"Borsos","year":"2023","journal-title":"arXiv preprint arXiv:2305.09636"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10096509"},{"key":"ref11","article-title":"Hifi-codec: Group-residual vector quantization for high fidelity audio codec","author":"Yang","year":"2023","journal-title":"arXiv preprint arXiv:2305.02765"},{"key":"ref12","article-title":"Fun-codec: A fundamental, reproducible and integrable open-source toolkit for neural speech codec","author":"Du","year":"2023","journal-title":"arXiv preprint arXiv:2309.07405"},{"key":"ref13","article-title":"Speechtokenizer: Unified speech tokenizer for speech large language models","author":"Zhang","year":"2023","journal-title":"arXiv preprint arXiv:2308.16692"},{"key":"ref14","article-title":"High-fidelity audio compression with improved rvqgan","author":"Kumar","year":"2023","journal-title":"arXiv preprint arXiv:2306.06546"},{"key":"ref15","article-title":"Naturalspeech 3: Zero-shot speech synthesis with factorized codec and diffusion models","author":"Ju","year":"2024","journal-title":"arXiv preprint arXiv:2403.03100"},{"key":"ref16","article-title":"Language-codec: Reducing the gaps between discrete codec representation and speech language models","author":"Ji","year":"2024","journal-title":"arXiv preprint arXiv:2402.12208"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP48485.2024.10448371"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP48485.2024.10445966"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP48485.2024.10447744"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP48485.2024.10447532"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP48485.2024.10446556"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2024.3506286"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2024.3417347"},{"key":"ref24","article-title":"Vocos: Closing the gap between timedomain and fourier-based neural vocoders for high-quality audio synthesis","author":"Siuzdak","year":"2023","journal-title":"arXiv preprint arXiv:2306.00814"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2024-1559"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/SLT61566.2024.10832228"},{"key":"ref27","article-title":"Uniaudio 1.5: Large language model-driven audio codec is a few-shot audio task learner","author":"Yang","year":"2024","journal-title":"arXiv preprint arXiv:2406.10056"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2024-1878"},{"key":"ref29","article-title":"Dasb-discrete audio and speech benchmark","author":"Mousavi","year":"2024","journal-title":"arXiv preprint arXiv:2406.14294"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.findings-acl.616"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178964"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2017-950"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7179090"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/SLT48900.2021.9383459"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2396"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9414922"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/TAFFC.2014.2336244"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pone.0196391"},{"key":"ref39","article-title":"Librimix: An opensource dataset for generalizable speech separation","author":"Cosentino","year":"2020","journal-title":"arXiv preprint arXiv:2005.11262"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1145\/2733373.2806390"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3133208"},{"key":"ref42","article-title":"Gunshots recorded in an open field using ipod touch devices","author":"Cooper","year":"2020","journal-title":"Dryad, Dataset"},{"key":"ref43","article-title":"Robust speech recognition via large-scale weak supervision","author":"Radford","year":"2022"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-2650"},{"key":"ref45","article-title":"emotion2vec: Self-supervised pre-training for speech emotion representation","author":"Ma","year":"2023","journal-title":"arXiv preprint arXiv:2312.15185"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/icassp48485.2024.10448504"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10095889"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2001.941023"},{"key":"ref49","article-title":"ludlows\/python-pesq: supporting for multi-processing features","author":"Wang","year":"2022"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2010.5495701"},{"key":"ref51","first-page":"28708","article-title":"Masked autoencoders that listen","volume":"35","author":"Huang","year":"2022","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3122291"},{"key":"ref53","first-page":"6840","article-title":"Denoising diffusion probabilistic models","volume":"33","author":"Ho","year":"2020","journal-title":"Advances in neural information processing systems"}],"event":{"name":"2024 IEEE Spoken Language Technology Workshop (SLT)","location":"Macao","start":{"date-parts":[[2024,12,2]]},"end":{"date-parts":[[2024,12,5]]}},"container-title":["2024 IEEE Spoken Language Technology Workshop (SLT)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/10830790\/10830793\/10832364.pdf?arnumber=10832364","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,1,17]],"date-time":"2025-01-17T07:50:42Z","timestamp":1737100242000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10832364\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,12,2]]},"references-count":53,"URL":"https:\/\/doi.org\/10.1109\/slt61566.2024.10832364","relation":{},"subject":[],"published":{"date-parts":[[2024,12,2]]}}}