{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,4,23]],"date-time":"2025-04-23T05:31:13Z","timestamp":1745386273630,"version":"3.33.0"},"reference-count":26,"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"}],"funder":[{"DOI":"10.13039\/501100010428","name":"Innovation and Technology Fund","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100010428","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2024,12,2]]},"DOI":"10.1109\/slt61566.2024.10832228","type":"proceedings-article","created":{"date-parts":[[2025,1,16]],"date-time":"2025-01-16T18:31:27Z","timestamp":1737052287000},"page":"548-553","source":"Crossref","is-referenced-by-count":3,"title":["Addressing Index Collapse of Large-Codebook Speech Tokenizer With Dual-Decoding Product-Quantized Variational Auto-Encoder"],"prefix":"10.1109","author":[{"given":"Haohan","family":"Guo","sequence":"first","affiliation":[{"name":"The Chinese University of Hong Kong,Hong Kong SAR,China"}]},{"given":"Fenglong","family":"Xie","sequence":"additional","affiliation":[{"name":"Xiaohongshu Inc,Shanghai,China"}]},{"given":"Dongchao","family":"Yang","sequence":"additional","affiliation":[{"name":"The Chinese University of Hong Kong,Hong Kong SAR,China"}]},{"given":"Hui","family":"Lu","sequence":"additional","affiliation":[{"name":"The Chinese University of Hong Kong,Hong Kong SAR,China"}]},{"given":"Xixin","family":"Wu","sequence":"additional","affiliation":[{"name":"The Chinese University of Hong Kong,Hong Kong SAR,China"}]},{"given":"Helen","family":"Meng","sequence":"additional","affiliation":[{"name":"The Chinese University of Hong Kong,Hong Kong SAR,China"}]}],"member":"263","reference":[{"article-title":"GPT-4 technical report","volume-title":"arXiv preprint arXiv:2303.08774","year":"2023","key":"ref1"},{"key":"ref2","article-title":"Scaling laws for neural language models","author":"Kaplan","year":"2020","journal-title":"arXiv preprint arXiv:2001.08361"},{"key":"ref3","article-title":"Textually pretrained speech language models","volume-title":"Proc. NeurIPS","volume":"36","author":"Hassid"},{"key":"ref4","article-title":"SpeechGen: Unlocking the generative power of speech language models with prompts","author":"Wu","year":"2023","journal-title":"arXiv preprint arXiv:2306.02207"},{"key":"ref5","article-title":"BASE TTS: Lessons from building a billion-parameter text-to-speech model on 100k hours of data","author":"\u0141ajszczak","year":"2024","journal-title":"arXiv preprint arXiv:2402.08093"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/LSP.2023.3308474"},{"key":"ref7","article-title":"Speech translation with large language models: An industrial practice","author":"Huang","year":"2023","journal-title":"arXiv preprint arXiv:2312.13585"},{"article-title":"Neural discrete representation learning","volume-title":"Proc. NeurIPS","author":"den Oord","key":"ref8"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8683277"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-283"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-489"},{"key":"ref12","article-title":"RepCodec: A speech representation codec for speech tokenization","author":"Huang","year":"2023","journal-title":"arXiv preprint arXiv:2309.00169"},{"article-title":"Straightening out the straight-through estimator: Overcoming optimization challenges in vector quantized networks","volume-title":"Proc. ICML","author":"Huh","key":"ref13"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2023.3272470"},{"key":"ref15","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":"ref16","article-title":"SpeechTokenizer: Unified speech tokenizer for speech large language models","author":"Zhang","year":"2023","journal-title":"arXiv preprint arXiv:2308.16692"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2010.57"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.02084"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9746682"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3122291"},{"key":"ref21","article-title":"QS-TTS: Towards semisupervised text-to-speech synthesis via vector-quantized selfsupervised speech representation learning","author":"Guo","year":"2023","journal-title":"arXiv preprint arXiv:2309.00126"},{"key":"ref22","article-title":"Better speech synthesis through scaling","author":"Betker","year":"2023","journal-title":"arXiv preprint arXiv:2305.07243"},{"article-title":"BigVGAN: A universal neural vocoder with large-scale training","volume-title":"Proc. ICLR","author":"Lee","key":"ref23"},{"key":"ref24","article-title":"Deep learning based assessment of synthetic speech naturalness","author":"Mittag","year":"2021","journal-title":"arXiv preprint arXiv:2104.11673"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.3390\/s101211259"},{"key":"ref26","article-title":"Finite scalar quantization: VQ-VAE made simple","author":"Mentzer","year":"2023","journal-title":"arXiv preprint arXiv:2309.15505"}],"event":{"name":"2024 IEEE Spoken Language Technology Workshop (SLT)","start":{"date-parts":[[2024,12,2]]},"location":"Macao","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\/10832228.pdf?arnumber=10832228","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,1,17]],"date-time":"2025-01-17T08:19:12Z","timestamp":1737101952000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10832228\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,12,2]]},"references-count":26,"URL":"https:\/\/doi.org\/10.1109\/slt61566.2024.10832228","relation":{},"subject":[],"published":{"date-parts":[[2024,12,2]]}}}