{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,22]],"date-time":"2026-04-22T18:40:47Z","timestamp":1776883247062,"version":"3.51.2"},"reference-count":34,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,4,6]],"date-time":"2025-04-06T00:00:00Z","timestamp":1743897600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,4,6]],"date-time":"2025-04-06T00:00:00Z","timestamp":1743897600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100012492","name":"Youth Innovation Promotion Association","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100012492","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100002367","name":"Chinese Academy of Sciences","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100002367","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,4,6]]},"DOI":"10.1109\/icassp49660.2025.10888680","type":"proceedings-article","created":{"date-parts":[[2025,3,12]],"date-time":"2025-03-12T17:15:19Z","timestamp":1741799719000},"page":"1-5","source":"Crossref","is-referenced-by-count":1,"title":["SLIDE: Integrating Speech Language Model with LLM for Spontaneous Spoken Dialogue Generation"],"prefix":"10.1109","author":[{"given":"Haitian","family":"Lu","sequence":"first","affiliation":[{"name":"Institute of Acoustics, CAS,Key Laboratory of Speech Acoustics and Content Understanding,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Gaofeng","family":"Cheng","sequence":"additional","affiliation":[{"name":"Institute of Acoustics, CAS,Key Laboratory of Speech Acoustics and Content Understanding,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Liuping","family":"Luo","sequence":"additional","affiliation":[{"name":"Guangdong Provincial,Public Security Department,Guangzhou,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Leying","family":"Zhang","sequence":"additional","affiliation":[{"name":"Shanghai Jiao Tong University,AudioCC Lab, MoE Key Lab of AI,CS Dept,Shanghai,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yanmin","family":"Qian","sequence":"additional","affiliation":[{"name":"Shanghai Jiao Tong University,AudioCC Lab, MoE Key Lab of AI,CS Dept,Shanghai,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Pengyuan","family":"Zhang","sequence":"additional","affiliation":[{"name":"Institute of Acoustics, CAS,Key Laboratory of Speech Acoustics and Content Understanding,China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1162\/tacl_a_00545"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2023.3288409"},{"key":"ref3","article-title":"Audiopalm: A large language model that can speak and listen","author":"Rubenstein","year":"2023"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1007\/s10462-022-10248-8"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1016\/j.specom.2005.05.009"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1016\/j.wocn.2010.08.002"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/LSP.2024.3453772"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053979"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2016-876"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/LSP.2024.3487795"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-33197-8_25"},{"key":"ref12","first-page":"101178","article-title":"Turn-taking in conversational systems and human-robot interaction: A review","volume-title":"Computer Speech Language","volume":"67","author":"Skantze","year":"2021"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.3389\/frobt.2022.933261"},{"key":"ref14","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":"ref15","article-title":"Covomix: Advancing zero-shot speech generation for human-like multi-talker conversations","author":"Zhang","year":"2024"},{"key":"ref16","article-title":"Towards human-like spoken dialogue generation between ai agents from written dialogue","author":"Mitsui","year":"2023"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3122291"},{"key":"ref18","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":"Advances in neural information processing systems"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/LSP.2023.3347148"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2022.3171967"},{"key":"ref21","article-title":"Attention is all you need","author":"Vaswani","year":"2017","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-475"},{"key":"ref23","first-page":"17022","article-title":"Hifi-gan: Generative adversarial networks for efficient and high fidelity speech synthesis","volume":"33","author":"Kong","year":"2020","journal-title":"Advances in neural information processing systems"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2024.3399607"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP48485.2024.10447929"},{"key":"ref26","first-page":"69","article-title":"The fisher corpus: A resource for the next generations of speech-to-text","volume-title":"LREC","volume":"4","author":"Cieri"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU57964.2023.10389648"},{"key":"ref28","first-page":"28492","article-title":"Robust speech recognition via large-scale weak supervision","volume-title":"International conference on machine learning","author":"Radford"},{"key":"ref29","article-title":"Gpt-4 technical report","author":"Achiam","year":"2023"},{"key":"ref30","article-title":"g2pe","author":"Park","year":"2019"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-1386"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2023-205"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2023-105"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.acldemos.30"}],"event":{"name":"ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","location":"Hyderabad, India","start":{"date-parts":[[2025,4,6]]},"end":{"date-parts":[[2025,4,11]]}},"container-title":["ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/10887540\/10887541\/10888680.pdf?arnumber=10888680","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,25]],"date-time":"2026-03-25T05:27:00Z","timestamp":1774416420000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10888680\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,4,6]]},"references-count":34,"URL":"https:\/\/doi.org\/10.1109\/icassp49660.2025.10888680","relation":{},"subject":[],"published":{"date-parts":[[2025,4,6]]}}}