{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,3]],"date-time":"2026-04-03T07:05:46Z","timestamp":1775199946012,"version":"3.50.1"},"reference-count":28,"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\/asru65441.2025.11434697","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":["ASR for Affective Speech: Investigating Impact of Emotion and Speech Generative Strategy"],"prefix":"10.1109","author":[{"given":"Ya-Tse","family":"Wu","sequence":"first","affiliation":[{"name":"National Tsing Hua University,Department of Electrical Engineering,Hsinchu,Taiwan"}]},{"given":"Chi-Chun","family":"Lee","sequence":"additional","affiliation":[{"name":"National Tsing Hua University,Hsinchu,Taiwan"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1007\/978-981-96-1452-3_21"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2014.2304637"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/N19-3003"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1080\/02699930441000445"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-15184-2_6"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/CDKE46621.2019.00009"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.3390\/s22051937"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8462624"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.3390\/s20082326"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2024-1645"},{"key":"ref11","article-title":"Cosyvoice 2: Scalable streaming speech synthesis with large language models","volume-title":"arXiv preprint arXiv:2412.10117","author":"Du","year":"2024"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1145\/3746027.3754829"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178964"},{"key":"ref14","article-title":"MaskGCT: Zero-shot text-to-speech with masked generative codec transformer","volume-title":"The Thirteenth International Conference on Learning Representations","author":"Wang"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9413391"},{"key":"ref16","article-title":"Qwen2-audio technical report","volume-title":"arXiv preprint arXiv:2407.10759","author":"Chu","year":"2024"},{"key":"ref17","first-page":"28492","article-title":"Robust speech recognition via large-scale weak supervision","volume-title":"International conference on machine learning.","author":"Radford"},{"key":"ref18","article-title":"Qwen technical report","volume-title":"arXiv preprint arXiv:2309.16609","author":"Bai","year":"2023"},{"key":"ref19","article-title":"Common voice: A massively-multilingual speech corpus","author":"Ardila","year":"2019","journal-title":"arXiv preprint arXiv:1912.06670"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-1180"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.21437\/odyssey.2024-35"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ACII59096.2023.10388175"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-299"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49660.2025.10890943"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v39i28.35383"},{"key":"ref26","article-title":"Pytorch: An imperative style, high-performance deep learning library","author":"Paszke","year":"2019","journal-title":"arXiv preprint arXiv:1912.01703"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/TAFFC.2017.2736999"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1007\/s10579-008-9076-6"}],"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\/11434697.pdf?arnumber=11434697","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,3]],"date-time":"2026-04-03T04:58:26Z","timestamp":1775192306000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11434697\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,12,6]]},"references-count":28,"URL":"https:\/\/doi.org\/10.1109\/asru65441.2025.11434697","relation":{},"subject":[],"published":{"date-parts":[[2025,12,6]]}}}