{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,31]],"date-time":"2025-10-31T07:30:50Z","timestamp":1761895850810,"version":"build-2065373602"},"reference-count":18,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,6,30]],"date-time":"2025-06-30T00:00:00Z","timestamp":1751241600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,6,30]],"date-time":"2025-06-30T00:00:00Z","timestamp":1751241600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/100006190","name":"Research and Development","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100006190","id-type":"DOI","asserted-by":"publisher"}]},{"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\/501100010256","name":"Guangzhou Municipal Science and Technology Project","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100010256","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,6,30]]},"DOI":"10.1109\/icme59968.2025.11209338","type":"proceedings-article","created":{"date-parts":[[2025,10,30]],"date-time":"2025-10-30T17:57:42Z","timestamp":1761847062000},"page":"1-6","source":"Crossref","is-referenced-by-count":0,"title":["DialogueAgents: A Hybrid Agent-Based Speech Synthesis Framework for Multi-Party Dialogue"],"prefix":"10.1109","author":[{"given":"Xiang","family":"Li","sequence":"first","affiliation":[{"name":"Beijing University of Posts and Telecommunications,State Key Laboratory of Networking and Switching Technology"}]},{"given":"Duyi","family":"Pan","sequence":"additional","affiliation":[{"name":"Hong Kong University of Science and Technology (Guangzhou),Department of Computer Science and Engineering"}]},{"given":"Hongru","family":"Xiao","sequence":"additional","affiliation":[{"name":"Hong Kong University of Science and Technology (Guangzhou),Department of Computer Science and Engineering"}]},{"given":"Jiale","family":"Han","sequence":"additional","affiliation":[{"name":"Hong Kong University of Science and Technology"}]},{"given":"Jing","family":"Tang","sequence":"additional","affiliation":[{"name":"Hong Kong University of Science and Technology (Guangzhou),Department of Computer Science and Engineering"}]},{"given":"Jiabao","family":"Ma","sequence":"additional","affiliation":[{"name":"Beijing University of Posts and Telecommunications,State Key Laboratory of Networking and Switching Technology"}]},{"given":"Wei","family":"Wang","sequence":"additional","affiliation":[{"name":"Hong Kong University of Science and Technology (Guangzhou),Department of Computer Science and Engineering"}]},{"given":"Bo","family":"Cheng","sequence":"additional","affiliation":[{"name":"Beijing University of Posts and Telecommunications,State Key Laboratory of Networking and Switching Technology"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2023-1095"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ICSDA.2013.6709856"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2024-2343"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10095751"},{"key":"ref5","article-title":"The fisher corpus: a resource for the next generations of speech-to-text","author":"Cieri","year":"2004","journal-title":"LREC"},{"article-title":"Advancing speech language models by scaling supervised fine-tuning with over 60,000 hours of synthetic speech dialogue data","year":"2024","author":"Zhao","key":"ref6"},{"key":"ref7","article-title":"Naturalspeech 2: Latent diffusion models are natural and zero-shot speech and singing synthesizers","author":"Shen","year":"2024","journal-title":"ICLR"},{"key":"ref8","article-title":"Dailydialog: A manually labelled multi-turn dialogue dataset","author":"Li","year":"2017","journal-title":"IJCNLP"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.acl-long.521"},{"key":"ref10","article-title":"Explain-analyze-generate: A sequential multi-agent collaboration method for complex reasoning","author":"Gu","year":"2025","journal-title":"COLING"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.emnlp-main.992"},{"key":"ref12","article-title":"Chateval: Towards better llm-based evaluators through multi-agent debate","volume-title":"ICLR.","author":"Chan","year":"2024"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.acl-long.381"},{"key":"ref14","article-title":"Speechagents: Human-communication simulation with multi-modal multi-agent systems","author":"Zhang","year":"2024","journal-title":"CoRR"},{"key":"ref15","article-title":"Common voice: A massively-multilingual speech corpus","author":"Ardila","year":"2020","journal-title":"LREC"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-439"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/icassp.2018.8461368"},{"key":"ref18","article-title":"Fastspeech 2: Fast and high-quality end-to-end text to speech","author":"Ren","year":"2021","journal-title":"ICLR"}],"event":{"name":"2025 IEEE International Conference on Multimedia and Expo (ICME)","start":{"date-parts":[[2025,6,30]]},"location":"Nantes, France","end":{"date-parts":[[2025,7,4]]}},"container-title":["2025 IEEE International Conference on Multimedia and Expo (ICME)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11208895\/11208897\/11209338.pdf?arnumber=11209338","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,31]],"date-time":"2025-10-31T06:00:37Z","timestamp":1761890437000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11209338\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,6,30]]},"references-count":18,"URL":"https:\/\/doi.org\/10.1109\/icme59968.2025.11209338","relation":{},"subject":[],"published":{"date-parts":[[2025,6,30]]}}}