{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,1,29]],"date-time":"2025-01-29T05:27:32Z","timestamp":1738128452754,"version":"3.33.0"},"reference-count":33,"publisher":"IEEE","license":[{"start":{"date-parts":[[2024,12,3]],"date-time":"2024-12-03T00:00:00Z","timestamp":1733184000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,12,3]],"date-time":"2024-12-03T00:00:00Z","timestamp":1733184000000},"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":[[2024,12,3]]},"DOI":"10.1109\/apsipaasc63619.2025.10849090","type":"proceedings-article","created":{"date-parts":[[2025,1,27]],"date-time":"2025-01-27T18:37:05Z","timestamp":1738003025000},"page":"1-6","source":"Crossref","is-referenced-by-count":0,"title":["NecoBERT: Self-Supervised Learning Model Trained by Masked Language Modeling on Rich Acoustic Features Derived from Neural Audio Codec"],"prefix":"10.1109","author":[{"given":"Wataru","family":"Nakata","sequence":"first","affiliation":[{"name":"The University of Tokyo,Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Takaaki","family":"Saeki","sequence":"additional","affiliation":[{"name":"The University of Tokyo,Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yuki","family":"Saito","sequence":"additional","affiliation":[{"name":"The University of Tokyo,Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Shinnosuke","family":"Takamichi","sequence":"additional","affiliation":[{"name":"The University of Tokyo,Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hiroshi","family":"Saruwatari","sequence":"additional","affiliation":[{"name":"The University of Tokyo,Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","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 for Computational Linguistics"},{"key":"ref2","first-page":"12 449","article-title":"Wav2vec 2.0: A framework for self-supervised learning of speech representations","volume-title":"Proc. NeurIPS","author":"Baevski"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3122291"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2022.3188113"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2021-1775"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2023-1823"},{"key":"ref7","first-page":"4171","article-title":"BERT: Pre-training of deep bidirectional transformers for language understanding","volume-title":"Proc. NAACL-HLT","author":"Devlin"},{"article-title":"Representation learning with contrastive predictive coding","year":"2018","author":"Oord","key":"ref8"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/taslp.2021.3129994"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/MP.2006.1664069"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053113"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/icassp39728.2021.9415079"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2023.3288409"},{"article-title":"Neural codec language models are zero-shot text to speech synthesizers","year":"2023","author":"Wang","key":"ref14"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461368"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33016706"},{"issue":"1","key":"ref17","first-page":"100","article-title":"A k-means clustering algorithm","volume":"28","author":"Hartigan","year":"1979","journal-title":"Journal of the Royal Statistical Society. Series C (Applied Statistics)"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2023-1292"},{"article-title":"VALL-T: Decoder-only generative Transducer for robust and decoding-controllable text-to-speech","year":"2024","author":"Du","key":"ref19"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1162\/tacl_a_00545"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.5555\/3295222.3295349"},{"key":"ref22","article-title":"High fidelity neural audio compression","author":"D\u00e9fossez","year":"2023","journal-title":"Transactions on Machine Learning Research"},{"article-title":"High-fidelity audio compression with improved RVQGAN","volume-title":"Proc. NeurIPS","author":"Kumar","key":"ref23"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU51503.2021.9688253"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1162\/tacl_a_00300"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178964"},{"article-title":"Decoupled weight decay regularization","volume-title":"Proc. ICLR","author":"Loshchilov","key":"ref27"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU57964.2023.10389699"},{"key":"ref29","first-page":"17 022","article-title":"HiFi-GAN: Generative adversarial networks for efficient and high fidelity speech synthesis","volume-title":"Advances in Neural Information Processing Systems","volume":"33","author":"Kong","year":"2020"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2019-2441"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/PACRIM.1993.407206"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461375"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1587\/transinf.2015EDP7457"}],"event":{"name":"2024 Asia Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC)","start":{"date-parts":[[2024,12,3]]},"location":"Macau, Macao","end":{"date-parts":[[2024,12,6]]}},"container-title":["2024 Asia Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/10848542\/10848533\/10849090.pdf?arnumber=10849090","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,1,28]],"date-time":"2025-01-28T06:10:37Z","timestamp":1738044637000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10849090\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,12,3]]},"references-count":33,"URL":"https:\/\/doi.org\/10.1109\/apsipaasc63619.2025.10849090","relation":{},"subject":[],"published":{"date-parts":[[2024,12,3]]}}}