{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,3]],"date-time":"2026-04-03T07:02:06Z","timestamp":1775199726905,"version":"3.50.1"},"reference-count":37,"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"}],"funder":[{"DOI":"10.13039\/501100001321","name":"National Research Foundation","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100001321","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,12,6]]},"DOI":"10.1109\/asru65441.2025.11434637","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":0,"title":["Incorporating Contextual Paralinguistic Understanding in Large Speech-Language Models"],"prefix":"10.1109","author":[{"given":"Qiongqiong","family":"Wang","sequence":"first","affiliation":[{"name":"Institute of Infocomm Research (I2R), A*STAR,Singapore"}]},{"given":"Hardik B.","family":"Sailor","sequence":"additional","affiliation":[{"name":"Institute of Infocomm Research (I2R), A*STAR,Singapore"}]},{"given":"Jeremy H. M.","family":"Wong","sequence":"additional","affiliation":[{"name":"Institute of Infocomm Research (I2R), A*STAR,Singapore"}]},{"given":"Tianchi","family":"Liu","sequence":"additional","affiliation":[{"name":"Institute of Infocomm Research (I2R), A*STAR,Singapore"}]},{"given":"Shuo","family":"Sun","sequence":"additional","affiliation":[{"name":"Institute of Infocomm Research (I2R), A*STAR,Singapore"}]},{"given":"Wenyu","family":"Zhang","sequence":"additional","affiliation":[{"name":"Institute of Infocomm Research (I2R), A*STAR,Singapore"}]},{"given":"Muhammad","family":"Huzaifah","sequence":"additional","affiliation":[{"name":"Institute of Infocomm Research (I2R), A*STAR,Singapore"}]},{"given":"Nancy","family":"Chen","sequence":"additional","affiliation":[{"name":"Institute of Infocomm Research (I2R), A*STAR,Singapore"}]},{"given":"Ai Ti","family":"Aw","sequence":"additional","affiliation":[{"name":"Institute of Infocomm Research (I2R), A*STAR,Singapore"}]}],"member":"263","reference":[{"key":"ref1","article-title":"Qwen-audio: Advancing universal audio understanding via unified large-scale audio-language models","author":"Chu","year":"2023","journal-title":"arXiv preprint arXiv:2311.07919"},{"key":"ref2","article-title":"Qwen2-audio technical report","volume-title":"arXiv preprint arXiv:2407.10759","author":"Chu","year":"2024"},{"key":"ref3","article-title":"GPT-4 technical report","volume-title":"arXiv preprint arXiv:2303.08774","author":"Achiama","year":"2023"},{"key":"ref4","article-title":"Salmonn: Towards generic hearing abilities for large language models","author":"Tang","year":"2023","journal-title":"arXiv preprint arXiv:2310.13289"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.acl-long.358"},{"key":"ref6","article-title":"Paralinguisticsaware speech-empowered large language models for natural conversation","volume-title":"The Thirty-eighth Annual Conference on Neural Information Processing Systems (NeurIPS)","author":"Kim"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2025-166"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.emnlp-main.1070"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2024-457"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/icassp49660.2025.10889444"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2025.findings-naacl.117"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP48485.2024.10447102"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i17.29902"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/APSIPAASC63619.2025.10848758"},{"key":"ref15","article-title":"VoxDialogue: Can spoken dialogue systems understand information beyond words?","volume-title":"International Conference on Learning Representations (ICLR)","author":"Cheng"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2025.acl-long.681"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU57964.2023.10389742"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2025.naacl-long.218"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP48485.2024.10448257"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.acl-long.109"},{"key":"ref21","article-title":"Listen, think, and understand","volume-title":"International Conference on Learning Representations (ICLR)","author":"Gong"},{"key":"ref22","article-title":"MMAU: A massive multi-task audio understanding and reasoning benchmark","volume-title":"International Conference on Learning Representations (ICLR)","author":"Sakshi"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2025-706"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2022.3188113"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.findings-acl.931"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2023.3263585"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2023-78"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D19-1410"},{"key":"ref29","article-title":"MERaLiON-AudioLLM: Technical report","volume-title":"arXiv preprint arXiv:2412.09818","author":"He","year":"2024"},{"key":"ref30","article-title":"Robust speech recognition via largescale weak supervision","volume-title":"Proceedings of the 40th International Conference on Machine Learning (ICML)","author":"Radford"},{"key":"ref31","article-title":"Gemma: Open models based on gemini research and technology","author":"Team","year":"2024","journal-title":"arXiv preprint arXiv:2403.08295"},{"key":"ref32","article-title":"Advancing Singlish understanding: Bridging the gap with datasets and multimodal models","author":"Wang","year":"2025","journal-title":"arXiv preprint arXiv:2501.01034"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-1525"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178964"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1007\/s10579-008-9076-6"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2017-950"},{"key":"ref37","article-title":"The MSP-Podcast corpus for speech emotion recognition","author":"Busso","year":"2023","journal-title":"IEEE Transactions on Affective Computing"}],"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\/11434637.pdf?arnumber=11434637","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,3]],"date-time":"2026-04-03T04:57:38Z","timestamp":1775192258000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11434637\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,12,6]]},"references-count":37,"URL":"https:\/\/doi.org\/10.1109\/asru65441.2025.11434637","relation":{},"subject":[],"published":{"date-parts":[[2025,12,6]]}}}