{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,22]],"date-time":"2026-04-22T19:15:00Z","timestamp":1776885300951,"version":"3.51.2"},"reference-count":47,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,12,6]],"date-time":"2025-12-06T00:00:00Z","timestamp":1764979200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,12,6]],"date-time":"2025-12-06T00:00:00Z","timestamp":1764979200000},"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":[[2025,12,6]]},"DOI":"10.1109\/asru65441.2025.11434685","type":"proceedings-article","created":{"date-parts":[[2026,4,2]],"date-time":"2026-04-02T19:48:04Z","timestamp":1775159284000},"page":"1-8","source":"Crossref","is-referenced-by-count":1,"title":["Benchmarking Prosody Encoding in Discrete Speech Tokens"],"prefix":"10.1109","author":[{"given":"Kentaro","family":"Onda","sequence":"first","affiliation":[{"name":"The University of Tokyo,Japan"}]},{"given":"Satoru","family":"Fukayama","sequence":"additional","affiliation":[{"name":"National Institute of Advanced Industrial Science and Technology (AIST),Japan"}]},{"given":"Daisuke","family":"Saito","sequence":"additional","affiliation":[{"name":"The University of Tokyo,Japan"}]},{"given":"Nobuaki","family":"Minematsu","sequence":"additional","affiliation":[{"name":"The University of Tokyo,Japan"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3122291"},{"key":"ref2","first-page":"12449","article-title":"wav2vec 2.0: A framework for self-supervised learning of speech representations","volume":"33","author":"Baevski","year":"2020","journal-title":"NeurIPS 2020"},{"key":"ref3","doi-asserted-by":"crossref","first-page":"1505","DOI":"10.1109\/JSTSP.2022.3188113","article-title":"WavLM: Large-scale self-supervised pre-training for full stack speech processing","volume":"16","author":"Chen","year":"2021","journal-title":"IEEE Journal of Selected Topics in Signal Processing"},{"key":"ref4","first-page":"244","article-title":"w2v-BERT: Combining contrastive learning and masked language modeling for self-supervised speech pre-training","volume-title":"2021 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","author":"Chung"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2022.3207050"},{"key":"ref6","article-title":"Recent advances in discrete speech tokens: A review","author":"Guo","year":"2025"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1162\/tacl_a_00430"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.findings-emnlp.1055"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/taslp.2023.3288409"},{"key":"ref10","article-title":"Audiopalm: A large language model that can speak and listen","author":"Rubenstein","year":"2023","journal-title":"arXiv preprint arXiv:2306.12925"},{"key":"ref11","article-title":"On the landscape of spoken language models: A comprehensive survey","author":"Arora"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2024-1878"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2023-2051"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP48485.2024.10447929"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP48485.2024.10447751"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2024-2135"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2024-2251"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP48485.2024.10446063"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSPW65056.2025.11011236"},{"key":"ref20","first-page":"465","article-title":"Augmentation invariant discrete representation for generative spoken language modeling","volume-title":"Proceedings of the 20th International Conference on Spoken Language Translation (IWSLT 2023)","author":"Gat"},{"key":"ref21","article-title":"Stab: Speech tokenizer assessment benchmark","author":"Vashishth","year":"2024"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/SLT61566.2024.10832198"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3129994"},{"key":"ref24","article-title":"High fidelity neural audio compression","author":"D\u00e9fossez","journal-title":"Transactions on Machine Learning Research, 2023, featured Certification, Reproducibility Certification."},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/SLT61566.2024.10832289"},{"key":"ref26","first-page":"10330","article-title":"Codec-SUPERB: An in-depth analysis of sound codec models","volume-title":"Findings of the Association for Computational Linguistics: ACL 2024","author":"Wu"},{"key":"ref27","article-title":"vec2wav 2.0: Advancing voice conversion via discrete token vocoders","author":"Guo","year":"2024","journal-title":"arXiv preprint arXiv:2409.01995"},{"key":"ref28","article-title":"Do discrete self-supervised representations of speech capture tone distinctions?","author":"Osakuade","year":"2024","journal-title":"arXiv preprint arXiv:2410.19935"},{"key":"ref29","first-page":"8666","article-title":"Text-free prosody-aware generative spoken language modeling","volume-title":"Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics","volume":"1","author":"Kharitonov"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10097097"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2023-438"},{"key":"ref32","first-page":"495","article-title":"EmphAssess: a prosodic benchmark on assessing emphasis transfer in speech-to-speech models","volume-title":"Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing","author":"de Seyssel"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49660.2025.10888561"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1587\/transinf.2015EDP7457"},{"key":"ref35","doi-asserted-by":"crossref","first-page":"250","DOI":"10.1162\/tacl_a_00545","article-title":"Generative spoken dialogue language modeling","volume":"11","author":"Nguyen","year":"2023","journal-title":"Transactions of the Association for Computational Linguistics"},{"key":"ref36","first-page":"18003","article-title":"Contentvec: An improved self-supervised speech representation by disentangling speakers","volume-title":"International conference on machine learning.","author":"Qian"},{"key":"ref37","first-page":"1298","article-title":"Data2vec: A general framework for self-supervised learning in speech, vision and language","volume-title":"International conference on machine learning.","author":"Baevski"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP48485.2024.10445906"},{"key":"ref39","first-page":"15747","article-title":"emotion2vec: Self-supervised pre-training for speech emotion representation","volume-title":"Findings of the Association for Computational Linguistics: ACL 2024","author":"Ma"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178964"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2025-577"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58589-1_42"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2025-310"},{"issue":"1","key":"ref44","doi-asserted-by":"crossref","first-page":"245","DOI":"10.1016\/S0167-6393(02)00107-3","article-title":"The analysis of speech in different temporal integration windows: cerebral lateralization as \u2018asymmetric sampling in time\u2019","volume":"41","author":"Poeppel","year":"2003","journal-title":"Speech Communication"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.35111\/17gk-bn40"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2025-593"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2023-1579"}],"event":{"name":"2025 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","location":"Honolulu, HI, USA","start":{"date-parts":[[2025,12,6]]},"end":{"date-parts":[[2025,12,10]]}},"container-title":["2025 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11434577\/11433836\/11434685.pdf?arnumber=11434685","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,3]],"date-time":"2026-04-03T04:58:14Z","timestamp":1775192294000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11434685\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,12,6]]},"references-count":47,"URL":"https:\/\/doi.org\/10.1109\/asru65441.2025.11434685","relation":{},"subject":[],"published":{"date-parts":[[2025,12,6]]}}}