{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,22]],"date-time":"2026-04-22T20:09:46Z","timestamp":1776888586223,"version":"3.51.2"},"reference-count":29,"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\/iscslp63861.2024.10800447","type":"proceedings-article","created":{"date-parts":[[2024,12,23]],"date-time":"2024-12-23T19:11:17Z","timestamp":1734981077000},"page":"586-590","source":"Crossref","is-referenced-by-count":9,"title":["E-Chat: Emotion-Sensitive Spoken Dialogue System with Large Language Models"],"prefix":"10.1109","author":[{"given":"Hongfei","family":"Xue","sequence":"first","affiliation":[{"name":"Northwestern Polytechnical University,Audio, Speech and Language Processing Group (ASLP@NPU),Xian"}]},{"given":"Yuhao","family":"Liang","sequence":"additional","affiliation":[{"name":"Northwestern Polytechnical University,Audio, Speech and Language Processing Group (ASLP@NPU),Xian"}]},{"given":"Bingshen","family":"Mu","sequence":"additional","affiliation":[{"name":"Northwestern Polytechnical University,Audio, Speech and Language Processing Group (ASLP@NPU),Xian"}]},{"given":"Shiliang","family":"Zhang","sequence":"additional","affiliation":[{"name":"Alibaba Group"}]},{"given":"Mengzhe","family":"Chen","sequence":"additional","affiliation":[{"name":"Alibaba Group"}]},{"given":"Qian","family":"Chen","sequence":"additional","affiliation":[{"name":"Alibaba Group"}]},{"given":"Lei","family":"Xie","sequence":"additional","affiliation":[{"name":"Northwestern Polytechnical University,Audio, Speech and Language Processing Group (ASLP@NPU),Xian"}]}],"member":"263","reference":[{"key":"ref1","article-title":"Introducing chatgpt","year":"2022"},{"key":"ref2","article-title":"Gpt-4 technical report","year":"2023","journal-title":"arXiv preprint"},{"key":"ref3","first-page":"1877","article-title":"Lan-guage models are few-shot learners","volume":"33","author":"Brown","year":"2020","journal-title":"Advances in neural information processing systems"},{"key":"ref4","article-title":"Palm 2 technical report","author":"Anil","year":"2023","journal-title":"arXiv preprint"},{"key":"ref5","article-title":"Llama: Open and efficient foundation language models","author":"Touvron","year":"2023","journal-title":"arXiv preprint"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.findings-emnlp.1055"},{"key":"ref7","article-title":"Audiopalm: A large language model that can speak and listen","author":"Rubenstein","year":"2023","journal-title":"arXiv preprint"},{"key":"ref8","article-title":"Listen, think, and understand","author":"Gong","year":"2023","journal-title":"arXiv preprint"},{"key":"ref9","first-page":"730","article-title":"BLIP-2: bootstrap-ping language-image pretraining with frozen image encoders and large language models","volume-title":"ICML","volume":"202","author":"Li","year":"2023"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.emnlp-demo.49"},{"key":"ref11","article-title":"Instructblip: Towards general-purpose vision-language models with instruction tuning","author":"Dai","year":"2023","journal-title":"NeurIPS"},{"key":"ref12","first-page":"492","article-title":"Robust speech recognition via large-scale weak su-pervision","volume":"202","author":"Radford","year":"2023","journal-title":"ICML"},{"key":"ref13","article-title":"Pengi: An audio language model for audio tasks","author":"Deshmukh","year":"2023","journal-title":"NeurIPS"},{"key":"ref14","article-title":"Salmonn: Towards generic hearing abilities for large language models","author":"Tang","year":"2023","journal-title":"arXiv preprint"},{"key":"ref15","article-title":"Qwen-audio: Advancing universal audio understanding via unified large-scale audio-language models","author":"Chu","year":"2023","journal-title":"arXiv preprint"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3122291"},{"key":"ref17","article-title":"Lora: Low-rank adaptation of large language models","author":"Hu","year":"2022","journal-title":"ICLR"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/icassp48485.2024.10445874"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref20","first-page":"477","article-title":"Dialogue-based neural learning to estimate the sentiment of a next upcoming ut-terance","author":"Bothe","year":"2017","journal-title":"ICANN"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01298-4_29"},{"key":"ref22","first-page":"2919","article-title":"Modelling context emotions using multitask learning for emotion controlled dialog generation","author":"Varshney","year":"2021","journal-title":"EACL"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.findings-acl.379"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP48485.2024.10446933"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9746682"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ICSDA.2017.8384449"},{"key":"ref27","article-title":"AISHELL-2: transforming mandarin ASR research into industrial scale","volume-title":"arXiv preprint","author":"Du","year":"2018"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i17.29902"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9747870"}],"event":{"name":"2024 IEEE 14th International Symposium on Chinese Spoken Language Processing (ISCSLP)","location":"Beijing, China","start":{"date-parts":[[2024,11,7]]},"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\/10800447.pdf?arnumber=10800447","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,12,24]],"date-time":"2024-12-24T06:26:27Z","timestamp":1735021587000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10800447\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,11,7]]},"references-count":29,"URL":"https:\/\/doi.org\/10.1109\/iscslp63861.2024.10800447","relation":{},"subject":[],"published":{"date-parts":[[2024,11,7]]}}}