{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,3]],"date-time":"2026-04-03T07:11:47Z","timestamp":1775200307380,"version":"3.50.1"},"reference-count":35,"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"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,12,6]]},"DOI":"10.1109\/asru65441.2025.11434787","type":"proceedings-article","created":{"date-parts":[[2026,4,2]],"date-time":"2026-04-02T19:48:04Z","timestamp":1775159284000},"page":"1-7","source":"Crossref","is-referenced-by-count":0,"title":["Speech in-context learning of paralinguistic tasks"],"prefix":"10.1109","author":[{"given":"Jeremy H. M.","family":"Wong","sequence":"first","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 F.","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":"Language models are few-shot learners","author":"Brown","year":"2020","journal-title":"NeurIPS1"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2025.naacl-long.354"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.acl-long.393"},{"key":"ref4","article-title":"SALMONN: towards generic hearing abilities for large language models","author":"Tang","year":"2024","journal-title":"ICLR"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.findings-emnlp.263"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU57964.2023.10389703"},{"key":"ref7","article-title":"Language models are unsupervised multitask learners","author":"Radford","year":"2019"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1007\/978-981-99-8181-6_6"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2023-1799"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49660.2025.10888591"},{"key":"ref11","first-page":"1352113525","article-title":"SALM: speech-augmented language model with in-context learning for speech recognition and translation","author":"Chen","year":"2024","journal-title":"ICASSP"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2024-1932"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2024.3436618"},{"key":"ref14","first-page":"28492","article-title":"Robust speech recognition via large-scale weak supervision","author":"Radford","year":"2023","journal-title":"ICML"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP48485.2024.10446502"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-11031"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2024-1346"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.findings-acl.728"},{"key":"ref19","article-title":"Phi-4-Mini technical report: compact yet powerful multimodal language models via mixture-of-LoRAs","volume-title":"Tech. Rep.","year":"2025"},{"key":"ref20","article-title":"MERaLiON-AudioLLM: bridging audio and language with large language models","volume-title":"Tech. Rep.","author":"He","year":"2025"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2025.ijcnlp-long.30"},{"key":"ref22","article-title":"Qwen2-Audio technical report","volume-title":"Tech. Rep.","author":"Chu","year":"2025"},{"key":"ref23","article-title":"Qwen technical report","volume-title":"Tech. Rep.","author":"Bai","year":"2023"},{"key":"ref24","article-title":"Qwen-Audio: advancing universal audio understanding via unified large-scale audio-language models","volume-title":"Tech. Rep.","author":"Chu","year":"2023"},{"key":"ref25","article-title":"Qwen2.5-Omni technical report","volume-title":"Tech. Rep.","year":"2025"},{"key":"ref26","article-title":"Qwen2.5 technical report","volume-title":"Tech. Rep.","year":"2025"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/TAFFC.2017.2736999"},{"key":"ref28","article-title":"Retrieval-augmented generation for knowledge-intensive NLP tasks","author":"Lewis","year":"2020","journal-title":"NeurIPS"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-16270-1_35"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP48485.2024.10448172"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-1259"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/asru57964.2023.10389678"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1007\/s10579-008-9076-6"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P19-1050"},{"key":"ref35","first-page":"8299","article-title":"Beyond the limits: a survey of techniques to extend the context length in large language models","author":"Wang","year":"2024","journal-title":"IJCAI"}],"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\/11434787.pdf?arnumber=11434787","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,3]],"date-time":"2026-04-03T04:59:48Z","timestamp":1775192388000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11434787\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,12,6]]},"references-count":35,"URL":"https:\/\/doi.org\/10.1109\/asru65441.2025.11434787","relation":{},"subject":[],"published":{"date-parts":[[2025,12,6]]}}}