{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,30]],"date-time":"2026-01-30T02:07:34Z","timestamp":1769738854914,"version":"3.49.0"},"reference-count":26,"publisher":"IEEE","license":[{"start":{"date-parts":[[2021,6,6]],"date-time":"2021-06-06T00:00:00Z","timestamp":1622937600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2021,6,6]],"date-time":"2021-06-06T00:00:00Z","timestamp":1622937600000},"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":[[2021,6,6]]},"DOI":"10.1109\/icassp39728.2021.9413680","type":"proceedings-article","created":{"date-parts":[[2021,5,13]],"date-time":"2021-05-13T19:53:45Z","timestamp":1620935625000},"page":"3050-3054","source":"Crossref","is-referenced-by-count":7,"title":["A Comparison of Discrete Latent Variable Models for Speech Representation Learning"],"prefix":"10.1109","author":[{"given":"Henry","family":"Zhou","sequence":"first","affiliation":[{"name":"University of Toronto"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Alexei","family":"Baevski","sequence":"additional","affiliation":[{"name":"Facebook AI Research"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Michael","family":"Auli","sequence":"additional","affiliation":[{"name":"Facebook AI Research"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref10","article-title":"Learning hierarchical discrete linguistic units from visually-grounded speech","author":"harwath","year":"2020","journal-title":"Proc of ICLR"},{"key":"ref11","article-title":"Wavenet: A generative model for raw audio","author":"van den oord","year":"2016","journal-title":"CoRR"},{"key":"ref12","article-title":"vq-wav2vec: Self-supervised learning of discrete speech representations","author":"baevski","year":"2020","journal-title":"Proc of ICLR"},{"key":"ref13","article-title":"Categorical reparameterization with gumbel-softmax","author":"jang","year":"2016"},{"key":"ref14","article-title":"Fast decoding in sequence models using discrete latent variables","author":"kaiser","year":"2018","journal-title":"CoRR"},{"key":"ref15","doi-asserted-by":"crossref","first-page":"117","DOI":"10.1109\/TPAMI.2010.57","article-title":"Product quan-tization for nearest neighbor search","volume":"33","author":"herv\u00e9","year":"2011","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"key":"ref16","article-title":"The challenge of realistic music generation: modelling raw audio at scale","author":"dieleman","year":"2018","journal-title":"Proc of NeurIPS"},{"key":"ref17","article-title":"wav2vec 2.0: A framework for self-supervised learning of speech representations","author":"baevski","year":"2020","journal-title":"Proc of NeurIPS"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178964"},{"key":"ref19","article-title":"Darpa timit acoustic phonetic continuous speech corpus cdrom","author":"garofolo","year":"1993"},{"key":"ref4","article-title":"Neural discrete representation learning","author":"van den oord","year":"2017","journal-title":"Proc of NeurIPS"},{"key":"ref3","article-title":"Learning discrete representations via information maximizing self-augmented training","author":"hu","year":"2017"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2019.2938863"},{"key":"ref5","article-title":"The challenge of realistic music generation: modelling raw audio at scale","author":"dieleman","year":"2018","journal-title":"CoRR"},{"key":"ref8","article-title":"vq-wav2vec: Self-supervised learning of discrete speech representations","author":"baevski","year":"2020","journal-title":"Proc of ICLR"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-1873"},{"key":"ref2","article-title":"Contrastive predictive coding based feature for automatic speaker verification","author":"lai","year":"2019","journal-title":"CoRR"},{"key":"ref9","article-title":"Towards unsupervised speech recognition and synthesis with quantized speech representation learning","author":"liu","year":"2019","journal-title":"ArXiv"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1186\/s13636-014-0044-3"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/N19-4009"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8683535"},{"key":"ref21","article-title":"SGDR: stochastic gradient descent with restarts","author":"loshchilov","year":"2016","journal-title":"CoRR"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D19-1539"},{"key":"ref23","article-title":"Bert: Pre-training of deep bidirectional transformers for language understanding","author":"devlin","year":"2019","journal-title":"Proc of NAACL"},{"key":"ref26","article-title":"Representation learning with contrastive predictive coding","author":"van den oord","year":"2018","journal-title":"ArXiv"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-1693"}],"event":{"name":"ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","location":"Toronto, ON, Canada","start":{"date-parts":[[2021,6,6]]},"end":{"date-parts":[[2021,6,11]]}},"container-title":["ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9413349\/9413350\/09413680.pdf?arnumber=9413680","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,6,3]],"date-time":"2022-06-03T19:49:22Z","timestamp":1654285762000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9413680\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,6,6]]},"references-count":26,"URL":"https:\/\/doi.org\/10.1109\/icassp39728.2021.9413680","relation":{},"subject":[],"published":{"date-parts":[[2021,6,6]]}}}