{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,22]],"date-time":"2026-04-22T19:35:43Z","timestamp":1776886543283,"version":"3.51.2"},"reference-count":41,"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\/slt61566.2024.10832266","type":"proceedings-article","created":{"date-parts":[[2025,1,16]],"date-time":"2025-01-16T18:31:27Z","timestamp":1737052287000},"page":"554-561","source":"Crossref","is-referenced-by-count":1,"title":["Investigating Neural Audio Codecs For Speech Language Model-Based Speech Generation"],"prefix":"10.1109","author":[{"given":"Jiaqi","family":"Li","sequence":"first","affiliation":[{"name":"The Chinese University of Hong Kong,Shenzhen,China"}]},{"given":"Dongmei","family":"Wang","sequence":"additional","affiliation":[{"name":"Microsoft, One Microsoft Way,Redmond,WA,USA"}]},{"given":"Xiaofei","family":"Wang","sequence":"additional","affiliation":[{"name":"Microsoft, One Microsoft Way,Redmond,WA,USA"}]},{"given":"Yao","family":"Qian","sequence":"additional","affiliation":[{"name":"Microsoft, One Microsoft Way,Redmond,WA,USA"}]},{"given":"Long","family":"Zhou","sequence":"additional","affiliation":[{"name":"Microsoft, One Microsoft Way,Redmond,WA,USA"}]},{"given":"Shujie","family":"Liu","sequence":"additional","affiliation":[{"name":"Microsoft, One Microsoft Way,Redmond,WA,USA"}]},{"given":"Midia","family":"Yousefi","sequence":"additional","affiliation":[{"name":"Microsoft, One Microsoft Way,Redmond,WA,USA"}]},{"given":"Canrun","family":"Li","sequence":"additional","affiliation":[{"name":"Microsoft, One Microsoft Way,Redmond,WA,USA"}]},{"given":"Chung-Hsien","family":"Tsai","sequence":"additional","affiliation":[{"name":"Microsoft, One Microsoft Way,Redmond,WA,USA"}]},{"given":"Zhen","family":"Xiao","sequence":"additional","affiliation":[{"name":"Microsoft, One Microsoft Way,Redmond,WA,USA"}]},{"given":"Yanqing","family":"Liu","sequence":"additional","affiliation":[{"name":"Microsoft, One Microsoft Way,Redmond,WA,USA"}]},{"given":"Junkun","family":"Chen","sequence":"additional","affiliation":[{"name":"Microsoft, One Microsoft Way,Redmond,WA,USA"}]},{"given":"Sheng","family":"Zhao","sequence":"additional","affiliation":[{"name":"Microsoft, One Microsoft Way,Redmond,WA,USA"}]},{"given":"Jinyu","family":"Li","sequence":"additional","affiliation":[{"name":"Microsoft, One Microsoft Way,Redmond,WA,USA"}]},{"given":"Zhizheng","family":"Wu","sequence":"additional","affiliation":[{"name":"The Chinese University of Hong Kong,Shenzhen,China"}]},{"given":"Michael","family":"Zeng","sequence":"additional","affiliation":[{"name":"Microsoft, One Microsoft Way,Redmond,WA,USA"}]}],"member":"263","reference":[{"key":"ref1","article-title":"Language models are few-shot learners","author":"Brown","year":"2020","journal-title":"arXiv: 2005.14165"},{"key":"ref2","article-title":"GPT-4 technical report","volume-title":"arXiv: 2303.08774","year":"2024"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2023.3288409"},{"key":"ref4","article-title":"Neural codec language models are zero-shot text to speech synthesizers","author":"Wang","year":"2023","journal-title":"arXiv: 2301.02111"},{"key":"ref5","article-title":"Soundstorm: Efficient parallel audio generation","author":"Borsos","year":"2023","journal-title":"arXiv: 2305.09636"},{"key":"ref6","article-title":"Audiopalm: A large language model that can speak and listen","author":"Rubenstein","year":"2023","journal-title":"arXiv: 2306.129251"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.21437\/SSW.2016"},{"key":"ref8","article-title":"vq-wav2vec: Self-supervisedlearning of discrete speech representations","volume-title":"International Conferenceon Learning Representations (ICLR)","author":"Baevski"},{"key":"ref9","article-title":"Hubert: Self-supervised speech representation learningby masked prediction of hidden units","author":"Hsu","year":"2021","journal-title":"arXiv:2106.07447"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU51503.2021.9688253"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/taslp.2021.3129994"},{"key":"ref12","article-title":"High fidelity neural audio compression","author":"D\u00e9fossez","year":"2022","journal-title":"arXiv:2210.13438"},{"key":"ref13","article-title":"High-fidelity audio compression with improved RVQGAN","volume-title":"Advances in Neural Information Processing Systems","author":"Kumar"},{"key":"ref14","first-page":"1336","article-title":"On generative spoken language modeling from raw audio","volume":"9","author":"Lakhotia","year":"2021","journal-title":"Transactions of the Association forComputational Linguistics"},{"key":"ref15","article-title":"Neural discrete representation learning","volume-title":"Advances in Neural Information Processing Systems","author":"van den Oord"},{"key":"ref16","article-title":"Vocos: Closing the gap between timedomain and fourier-based neural vocoders for high-quality audio synthesis","volume-title":"International Conference on Learning representations, ICLR","author":"Siuzdak"},{"key":"ref17","article-title":"Neural networks fail to learn periodic functions and how to fix it","volume-title":"Advances in Neural Information Processing Systems","author":"Liu"},{"key":"ref18","article-title":"Naturalspeech 3: Zero-shot speech synthesiswith factorized codec and diffusion models","volume-title":"arXiv:2403.03100","author":"Ju","year":"2024"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2024.3506286"},{"key":"ref20","article-title":"Promptcodec: High-fidelity neural speech codec using disentangled representation learning-based adaptive feature-aware prompt encoders","author":"Pan","year":"2024","journal-title":"arXiv:2404.02702"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP48485.2024.10448454"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2024.3469530"},{"key":"ref23","article-title":"Singlecodec: Single-codebook speech codec towards high-performance speech generation","author":"Li","year":"2024","journal-title":"arXiv:2406.07422"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.findings-acl.616"},{"key":"ref25","article-title":"Towards audio language modeling - an overview","author":"Wu","year":"2024","journal-title":"arXiv:2402.13236"},{"key":"ref26","article-title":"Masked audio generation using a single non-autoregressive transformer","volume-title":"International conference on learning represenations (ICLR)","author":"Ziv"},{"key":"ref27","article-title":"Classifier-free diffusion guidance","author":"Ho","year":"2024","journal-title":"arXiv:2207.12598"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2023.3270264"},{"key":"ref29","article-title":"Vall-e 2: Neural codec language models are human parity zero-shot text to speech synthesizers","author":"Chen","year":"2024","journal-title":"arXiv preprint arXiv:2406.05370"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01103"},{"key":"ref31","first-page":"7669","article-title":"Librilight: A benchmark for asr with limited or no supervision","volume-title":"ICASSP 2020-2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","author":"Kahn"},{"key":"ref32","article-title":"Hifigan: generative adversarial networks for efficient and high fidelity speech synthesis","volume-title":"Proceedings of the 34th International Conference on Neural Information Processing Systems","author":"Kong"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178964"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2001.941023"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2010.5495701"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/QoMEX48832.2020.9123150"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/PACRIM.1993.407206"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2022.3188113"},{"key":"ref39","article-title":"Common voice: A massively-multilingual speech corpus","author":"Ardila","year":"2020","journal-title":"arXiv preprint arXiv:1912.06670"},{"key":"ref40","article-title":"Voicebox: Text-guided multilingual universal speech generation at scale","author":"Le","year":"2023","journal-title":"arXiv:2306.15687"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-299"}],"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\/10832266.pdf?arnumber=10832266","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,1,17]],"date-time":"2025-01-17T08:19:07Z","timestamp":1737101947000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10832266\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,12,2]]},"references-count":41,"URL":"https:\/\/doi.org\/10.1109\/slt61566.2024.10832266","relation":{},"subject":[],"published":{"date-parts":[[2024,12,2]]}}}