{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,5,28]],"date-time":"2025-05-28T04:02:26Z","timestamp":1748404946923,"version":"3.41.0"},"reference-count":25,"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\/iscslp63861.2024.10800745","type":"proceedings-article","created":{"date-parts":[[2024,12,23]],"date-time":"2024-12-23T19:11:17Z","timestamp":1734981077000},"page":"417-420","source":"Crossref","is-referenced-by-count":0,"title":["EmoSpeech: A Corpus of Emotionally Rich and Contextually Detailed Speech Annotations"],"prefix":"10.1109","author":[{"given":"Weizhen","family":"Bian","sequence":"first","affiliation":[{"name":"Independent Researcher"}]},{"given":"Yubo","family":"Zhou","sequence":"additional","affiliation":[{"name":"Hong Kong Baptist University."}]},{"given":"Kaitai","family":"Zhang","sequence":"additional","affiliation":[{"name":"Hong Kong Baptist University."}]},{"given":"Xiaohan","family":"Gu","sequence":"additional","affiliation":[{"name":"Hong Kong Baptist University."}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.acl-short.59"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1186\/s13636-024-00329-7"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1007\/978-981-97-5489-2_24"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1007\/s10579-008-9076-6"},{"key":"ref5","first-page":"2023","article-title":"Utilizing large language models to simplify radiology reports: a comparative analysis of chatgpt3. 5, chatgpt4. 0, google bard, and microsoft bing","author":"Doshi","year":"2023","journal-title":"medRxiv"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2023-1428"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10095621"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10096285"},{"journal-title":"An overview oftext-to-speech systems and media applications","year":"2023","author":"Hasanabadi","key":"ref9"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3122291"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2024-692"},{"key":"ref12","first-page":"28492","article-title":"Robust speech recognition via large-scale weak supervision","volume-title":"International conference on machine learning","author":"Radford","year":"2023"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.21437\/Eurospeech.2003-120"},{"journal-title":"Naturalspeech 2: La-tent diffusion models are natural and zero-shot speech and singing synthesizers","year":"2023","author":"Shen","key":"ref14"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1145\/3474085.3475373"},{"journal-title":"Llama: Open and efficient foundation language models","year":"2023","author":"Touvron","key":"ref16"},{"journal-title":"Multi-modal emotion recognition on iemocap dataset using deep learning","year":"2018","author":"Tripathi","key":"ref17"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053732"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i17.29902"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2024.3402088"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1007\/978-981-99-2401-1_18"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1145\/3664647.3681044"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1145\/3581783.3612061"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-11133"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9413391"}],"event":{"name":"2024 IEEE 14th International Symposium on Chinese Spoken Language Processing (ISCSLP)","start":{"date-parts":[[2024,11,7]]},"location":"Beijing, China","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\/10800745.pdf?arnumber=10800745","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,5,27]],"date-time":"2025-05-27T04:31:36Z","timestamp":1748320296000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10800745\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,11,7]]},"references-count":25,"URL":"https:\/\/doi.org\/10.1109\/iscslp63861.2024.10800745","relation":{},"subject":[],"published":{"date-parts":[[2024,11,7]]}}}