{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,12,25]],"date-time":"2024-12-25T05:26:12Z","timestamp":1735104372528,"version":"3.32.0"},"reference-count":35,"publisher":"IEEE","license":[{"start":{"date-parts":[[2024,11,7]],"date-time":"2024-11-07T00:00:00Z","timestamp":1730937600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,11,7]],"date-time":"2024-11-07T00:00:00Z","timestamp":1730937600000},"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":[[2024,11,7]]},"DOI":"10.1109\/iscslp63861.2024.10800009","type":"proceedings-article","created":{"date-parts":[[2024,12,23]],"date-time":"2024-12-23T19:11:17Z","timestamp":1734981077000},"page":"641-645","source":"Crossref","is-referenced-by-count":0,"title":["The X-Lance Technical Report for Interspeech 2024 Speech Processing using Discrete Speech Unit Challenge"],"prefix":"10.1109","author":[{"given":"Yiwei","family":"Guo","sequence":"first","affiliation":[{"name":"Shanghai Jiao Tong University,MoE Key Lab of Artificial Intelligence, X-LANCE Lab"}]},{"given":"Chenrun","family":"Wang","sequence":"additional","affiliation":[{"name":"Shanghai Jiao Tong University,MoE Key Lab of Artificial Intelligence, X-LANCE Lab"}]},{"given":"Yifan","family":"Yang","sequence":"additional","affiliation":[{"name":"Shanghai Jiao Tong University,MoE Key Lab of Artificial Intelligence, X-LANCE Lab"}]},{"given":"Hankun","family":"Wang","sequence":"additional","affiliation":[{"name":"Shanghai Jiao Tong University,MoE Key Lab of Artificial Intelligence, X-LANCE Lab"}]},{"given":"Ziyang","family":"Ma","sequence":"additional","affiliation":[{"name":"Shanghai Jiao Tong University,MoE Key Lab of Artificial Intelligence, X-LANCE Lab"}]},{"given":"Chenpeng","family":"Du","sequence":"additional","affiliation":[{"name":"Shanghai Jiao Tong University,MoE Key Lab of Artificial Intelligence, X-LANCE Lab"}]},{"given":"Shuai","family":"Wang","sequence":"additional","affiliation":[{"name":"Shenzhen Research Institute of Big Data"}]},{"given":"Hanzheng","family":"Li","sequence":"additional","affiliation":[{"name":"AISpeech Ltd"}]},{"given":"Xu","family":"Li","sequence":"additional","affiliation":[{"name":"AISpeech Ltd"}]},{"given":"Shuai","family":"Fan","sequence":"additional","affiliation":[{"name":"AISpeech Ltd"}]},{"given":"Hui","family":"Zhang","sequence":"additional","affiliation":[{"name":"AISpeech Ltd"}]},{"given":"Xie","family":"Chen","sequence":"additional","affiliation":[{"name":"Shanghai Jiao Tong University,MoE Key Lab of Artificial Intelligence, X-LANCE Lab"}]},{"given":"Kai","family":"Yu","sequence":"additional","affiliation":[{"name":"Shanghai Jiao Tong University,MoE Key Lab of Artificial Intelligence, X-LANCE Lab"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/icassp48485.2024.10447523"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-489"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2023.3288409"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1162\/tacl_a_00618"},{"key":"ref5","article-title":"Neural codec language mod-els are zero-shot text to speech synthesizers","author":"Wang","year":"2023","journal-title":"arXiv preprint"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i16.29747"},{"key":"ref7","article-title":"Vec-Tok Speech: speech vectorization and tokenization for neu-ral speech generation","author":"Zhu","year":"2023","journal-title":"arXiv preprint"},{"key":"ref8","article-title":"ELLA-V: Sta-ble neural codec language modeling with alignment-guided se-quence reordering","author":"Song","year":"2024","journal-title":"arXiv preprint"},{"key":"ref9","first-page":"12449","article-title":"wav2vec 2.0: A framework for self-supervised learning of speech representations","volume-title":"Advances in Neural Information Processing Systems","volume":"33","author":"Baevski","year":"2020"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9052942"},{"article-title":"vq-wav2vec: Self-supervised learning of discrete speech representations","volume-title":"Inter-national Conference on Learning Representations","author":"Baevski","key":"ref11"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3122291"},{"key":"ref13","article-title":"High fidelity neural audio compression","author":"D\u00e9fossez","year":"2022","journal-title":"arXiv preprint"},{"article-title":"HiFi-GAN: Generative adversarial networks for efficient and high fidelity speech synthesis","volume-title":"Proc. NeurIPS","author":"Kong","key":"ref14"},{"volume-title":"The LJ Speech Dataset","year":"2017","author":"Ito","key":"ref15"},{"key":"ref16","article-title":"The Kaldi speech recognition toolkit","volume-title":"IEEE 2011 workshop on automatic speech recognition and understanding. IEEE Sig-nal Processing Society","author":"Povey","year":"2011"},{"key":"ref17","article-title":"RAD-TTS: Parallel flow-based TTS with robust alignment learning and diverse synthesis","volume-title":"ICML Workshop on Invertible Neural Networks, Normalizing Flows, and Explicit Likelihood Models","author":"Shih","year":"2021"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2441"},{"key":"ref19","first-page":"23","article-title":"Robust speech recognition via large-scale weak su-pervision","volume-title":"Proceedings of the 40th International Conference on Machine Learning","author":"Radford"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-439"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-48"},{"key":"ref22","article-title":"Make-A-Voice: Uni-fied voice synthesis with discrete representation","author":"Huang","year":"2023","journal-title":"arXiv preprint"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3129994"},{"key":"ref24","article-title":"High-fidelity audio compression with improved RVQGAN","volume":"36","author":"Kumar","year":"2024","journal-title":"Ad-vances in Neural Information Processing Systems"},{"volume-title":"MUSDB18 - a corpus for music separation","year":"2017","author":"Rafii","key":"ref25"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2022.3188113"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP48485.2024.10447751"},{"article-title":"Zipformer: A faster and better encoder for automatic speech recognition","volume-title":"The Twelfth International Conference on Learning Representations","author":"Yao","key":"ref28"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2013.6638947"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2022-10340"},{"key":"ref31","article-title":"Speech recognition with next-generation kaldi (k2, lhotse, icefall)","author":"Povey","year":"2021","journal-title":"Interspeech: tutori-als"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9054419"},{"key":"ref33","article-title":"Neural machine trans-lation of rare words with subword units","volume-title":"Proc. ACL, Berlin","author":"Sennrich","year":"2016"},{"key":"ref34","article-title":"Lib-riSpeech: an asr corpus based on public domain audio books","volume-title":"Proc. ICASSP, South Brisbane","author":"Panayotov","year":"2015"},{"key":"ref35","article-title":"ML-SUPERB: Multilingual speech universal performance bench-mark","author":"Shi","year":"2023","journal-title":"arXiv preprint"}],"event":{"name":"2024 IEEE 14th International Symposium on Chinese Spoken Language Processing (ISCSLP)","start":{"date-parts":[[2024,11,7]]},"location":"Beijing, China","end":{"date-parts":[[2024,11,10]]}},"container-title":["2024 IEEE 14th International Symposium on Chinese Spoken Language Processing (ISCSLP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/10799944\/10799969\/10800009.pdf?arnumber=10800009","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,12,24]],"date-time":"2024-12-24T19:11:14Z","timestamp":1735067474000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10800009\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,11,7]]},"references-count":35,"URL":"https:\/\/doi.org\/10.1109\/iscslp63861.2024.10800009","relation":{},"subject":[],"published":{"date-parts":[[2024,11,7]]}}}