{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,15]],"date-time":"2026-06-15T15:26:57Z","timestamp":1781537217421,"version":"3.54.5"},"reference-count":42,"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\/501100002642","name":"Korea University","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100002642","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\/icassp49660.2025.10888227","type":"proceedings-article","created":{"date-parts":[[2025,3,12]],"date-time":"2025-03-12T13:52:43Z","timestamp":1741787563000},"page":"1-5","source":"Crossref","is-referenced-by-count":3,"title":["JELLY: Joint Emotion Recognition and Context Reasoning with LLMs for Conversational Speech Synthesis"],"prefix":"10.1109","author":[{"given":"Jun-Hyeok","family":"Cha","sequence":"first","affiliation":[{"name":"Korea University,Dept. of Artificial Intelligence,Seoul,Korea"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Seung-Bin","family":"Kim","sequence":"additional","affiliation":[{"name":"Korea University,Dept. of Artificial Intelligence,Seoul,Korea"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hyung-Seok","family":"Oh","sequence":"additional","affiliation":[{"name":"Korea University,Dept. of Artificial Intelligence,Seoul,Korea"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Seong-Whan","family":"Lee","sequence":"additional","affiliation":[{"name":"Korea University,Dept. of Artificial Intelligence,Seoul,Korea"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461368"},{"key":"ref2","article-title":"FastSpeech 2: Fast and High-Quality End-to-End Text to Speech","volume-title":"Proc. Int. Conf. Learn. Represent. (ICLR)","author":"Ren"},{"key":"ref3","article-title":"HierSpeech: Bridging the Gap between Text and Speech by Hierarchical Variational Inference using Self-supervised Representations for Speech Synthesis","author":"Lee","year":"2022","journal-title":"Adv. Neural Inf. Process. Syst. (NeurIPS)"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP48485.2024.10448291"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/icassp48485.2024.10445948"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/SLT48900.2021.9383460"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9747837"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10096905"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP48485.2024.10446506"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP48485.2024.10448356"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/72.557671"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.3390\/brainsci9120348"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/SMC.2019.8914645"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/EMBC44109.2020.9175874"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1126\/scirobotics.abb9764"},{"key":"ref16","article-title":"Periodwave: Multi-period flow matching for high-fidelity waveform generation","author":"Lee","year":"2024"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9747098"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2024.3395994"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2024-398"},{"key":"ref20","article-title":"DurFlex-EVC: Duration-Flexible Emotional Voice Conversion with Parallel Generation","author":"Oh","year":"2024"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i17.29833"},{"key":"ref22","article-title":"Internlm-xcomposer2: Mastering free-form text-image composition and comprehension in vision-language large model","author":"Dong","year":"2024"},{"key":"ref23","article-title":"BLSP-KD: Bootstrapping Language-Speech Pre-training via Knowledge Distillation","author":"Wang","year":"2024"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2023-2193"},{"key":"ref25","article-title":"BLIP-2: Bootstrapping Language-Image Pre-training with Frozen Image Encoders and Large Language Models","volume-title":"Proc. Int. Conf. Mach. Learn. (ICML)","author":"Li"},{"key":"ref26","article-title":"Robust Speech Recognition via Large-Scale Weak Supervision","volume-title":"Proc. Int. Conf. Mach. Learn. (ICML)","author":"Radford"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU57964.2023.10389742"},{"key":"ref28","article-title":"HiFi-GAN: Generative Adversarial Networks for Efficient and High Fidelity Speech Synthesis","author":"Kong","year":"2020","journal-title":"Adv. Neural Inf. Process. Syst. (NeurIPS)"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10095751"},{"key":"ref30","article-title":"DailyDialog: A Manually Labelled Multi-turn Dialogue Dataset","author":"Li","year":"2017","journal-title":"Int. Jt. Conf. Nat. Lang. Process. (IJCNLP)"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/TAFFC.2014.2336244"},{"key":"ref32","article-title":"The emotional voices database: Towards controlling the emotion dimension in voice generation systems","author":"Adigwe","year":"2018"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1007\/s10579-008-9076-6"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58589-1_42"},{"key":"ref35","article-title":"Toronto emotional speech set (tess)-younger talker happy","author":"Dupuis","year":"2010"},{"key":"ref36","article-title":"Vicuna: An Open-Source Chatbot Impressing GPT-4 with 90%* ChatGPT Quality","author":"Chiang","year":"2023"},{"key":"ref37","article-title":"LLama: Open and efficient foundation language models","author":"Touvron","year":"2023"},{"key":"ref38","article-title":"Decoupled Weight Decay Regularization","volume-title":"Int. Conf. Learn. Represent. (ICLR)","author":"Loshchilov"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.findings-acl.931"},{"key":"ref40","article-title":"wav2vec 2.0: A Framework for Self-Supervised Learning of Speech Representations","author":"Baevski","year":"2020","journal-title":"Adv. Neural Inf. Process. Syst. (NeurIPS)"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2019.2892235"},{"key":"ref42","article-title":"LoRA: Low-Rank Adaptation of Large Language Models","volume-title":"Proc. Int. Conf. Learn. Represent. (ICLR)","author":"J Hu"}],"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\/10888227.pdf?arnumber=10888227","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,25]],"date-time":"2026-03-25T05:25:59Z","timestamp":1774416359000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10888227\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,4,6]]},"references-count":42,"URL":"https:\/\/doi.org\/10.1109\/icassp49660.2025.10888227","relation":{},"subject":[],"published":{"date-parts":[[2025,4,6]]}}}