{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,3]],"date-time":"2026-04-03T07:08:13Z","timestamp":1775200093487,"version":"3.50.1"},"reference-count":45,"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\/asru65441.2025.11434728","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":["Few-shot Personalization via In-Context Learning for Speech Emotion Recognition based on Speech-Language Model"],"prefix":"10.1109","author":[{"given":"Mana","family":"Ihori","sequence":"first","affiliation":[{"name":"NTT, Inc.,Human Informatics Laboratories,Japan"}]},{"given":"Taiga","family":"Yamane","sequence":"additional","affiliation":[{"name":"NTT, Inc.,Human Informatics Laboratories,Japan"}]},{"given":"Naotaka","family":"Kawata","sequence":"additional","affiliation":[{"name":"NTT, Inc.,Human Informatics Laboratories,Japan"}]},{"given":"Naoki","family":"Makishima","sequence":"additional","affiliation":[{"name":"NTT, Inc.,Human Informatics Laboratories,Japan"}]},{"given":"Tomohiro","family":"Tanaka","sequence":"additional","affiliation":[{"name":"NTT, Inc.,Human Informatics Laboratories,Japan"}]},{"given":"Satoshi","family":"Suzuki","sequence":"additional","affiliation":[{"name":"NTT, Inc.,Human Informatics Laboratories,Japan"}]},{"given":"Shota","family":"Orihashi","sequence":"additional","affiliation":[{"name":"NTT, Inc.,Human Informatics Laboratories,Japan"}]},{"given":"Ryo","family":"Masumura","sequence":"additional","affiliation":[{"name":"NTT, Inc.,Human Informatics Laboratories,Japan"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2020.2966857"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.3115\/1620932.1620941"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1016\/0092-6566(87)90023-7"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1037\/\/0033-2909.115.1.102"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1037\/0882-7974.12.4.590"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1037\/a0030737"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1037\/pspp0000036"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2022.3178232"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.21437\/ICSLP.1998-244"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2022.3171965"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICME51207.2021.9428217"},{"key":"ref12","article-title":"Exploring speaker enrolment for few-shot personalisation in emotional vocalisation prediction","author":"Triantafyllopoulos","year":"2022","journal-title":"arXiv preprint arXiv:2206.06680"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2024-98"},{"key":"ref14","first-page":"1877","article-title":"Language Models are Few-Shot Learners","volume-title":"Proc. Advances in Neural Information Processing Systems (NeurIPS)","author":"Brown"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/taslpro.2025.3648793"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i17.29902"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.naacl-main.201"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2023.3263585"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/SLT.2018.8639583"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9054629"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-3005"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2005-379"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ICME.2005.1521560"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2014.6854514"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7953138"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01418-6_76"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2594"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-573"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/TAFFC.2024.3498937"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9747460"},{"key":"ref31","article-title":"SALMONN: Towards Generic Hearing Abilities for Large Language Models","author":"Changli","year":"2023","journal-title":"arXiv preprint arXiv:2310.13289"},{"key":"ref32","first-page":"25 125","article-title":"Audio Flamingo: A Novel Audio Language Model with Few-Shot Learning and Dialogue Abilities","volume-title":"Proc. International Conference on Machine Learning (ICML)","author":"Kong"},{"key":"ref33","article-title":"Qwen2-Audio Technical Report","volume-title":"arXiv preprint arXiv:2407.10759","author":"Chu","year":"2024"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP48485.2024.10447553"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP48485.2024.10446502"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2025.emnlp-main.219"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2024-1346"},{"key":"ref38","first-page":"4139","article-title":"Exploring InContext Learning of Textless Speech Language Model for Speech Classification Tasks","volume-title":"Proc. Conference of the International Speech Communication Association (INTERSPEECH)","author":"Chang"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref40","article-title":"Finetuned Language Models are Zero-Shot Learners","volume-title":"Proc. International Conference on Learning Representations (ICLR)","author":"Wei"},{"key":"ref41","first-page":"19730","article-title":"BLIP-2: Bootstrapping LanguageImage Pre-training with Frozen Image Encoders and Large Language Models","volume-title":"Proc. International Conference on Machine Learning (ICML)","author":"Li"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1007\/s10579-008-9076-6"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2005-446"},{"key":"ref44","first-page":"53","article-title":"Speaker-Dependent Audio-Visual Emotion Recognition","volume-title":"Proc. International Conference on AuditoryVisual Speech Processing (AVSP)","volume":"2009","author":"Haq"},{"key":"ref45","article-title":"U12: Unifying language learning paradigms","volume-title":"Proc. International Conference on Learning Representations (ICLR)","author":"Tay"}],"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\/11434728.pdf?arnumber=11434728","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,3]],"date-time":"2026-04-03T04:59:00Z","timestamp":1775192340000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11434728\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,12,6]]},"references-count":45,"URL":"https:\/\/doi.org\/10.1109\/asru65441.2025.11434728","relation":{},"subject":[],"published":{"date-parts":[[2025,12,6]]}}}