{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,3]],"date-time":"2026-04-03T07:01:28Z","timestamp":1775199688272,"version":"3.50.1"},"reference-count":44,"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\/asru65441.2025.11434633","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":["Expressive Speech Retrieval using Natural Language Descriptions of Speaking Style"],"prefix":"10.1109","author":[{"given":"Wonjune","family":"Kang","sequence":"first","affiliation":[{"name":"Massachusetts Institute of Technology,Cambridge,MA,USA"}]},{"given":"Deb","family":"Roy","sequence":"additional","affiliation":[{"name":"Massachusetts Institute of Technology,Cambridge,MA,USA"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/MSP.2008.917992"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU.2009.5372952"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1561\/1500000020"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2015.2438543"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP48485.2024.10448210"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP48485.2024.10447448"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2025.acl-long.613"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49660.2025.10888900"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP48485.2024.10448213"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10095969"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1007\/s10579-008-9076-6"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1016\/j.specom.2021.11.006"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2023-1905"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10096285"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2023-1779"},{"key":"ref16","article-title":"PromptTTS 2: Describing and generating voices with text prompt","volume-title":"International Conference on Learning Representations","author":"Leng"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2024-1432"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP48485.2024.10445977"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2024-692"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1145\/1277741.1277847"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1145\/1658377.1658379"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2013.2285469"},{"key":"ref23","first-page":"13","article-title":"Evaluating ASR output for information retrieval","author":"van der Werff","year":"2007","journal-title":"Searching Spontaneous Conversational Speech"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-00958-7_80"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/JPROC.2012.2236631"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2010-262"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/ICME.2013.6607546"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2013.6639247"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP48485.2024.10448030"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/icassp49660.2025.10890201"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2022.3188113"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.findings-acl.931"},{"key":"ref33","first-page":"4171","article-title":"BERT: Pretraining of deep bidirectional transformers for language understanding","volume-title":"Proceedings of the Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies","volume":"1","author":"Devlin"},{"key":"ref34","article-title":"RoBERTa: A robustly optimized BERT pretraining approach","author":"Liu","year":"2019","journal-title":"arXiv preprint arXiv:1907.11692"},{"issue":"140","key":"ref35","first-page":"1","article-title":"Exploring the limits of transfer learning with a unified text-to-text transformer","volume":"21","author":"Raffel","year":"2020","journal-title":"Journal of Machine Learning Research"},{"key":"ref36","first-page":"22631","article-title":"The flan collection: Designing data and methods for effective instruction tuning","volume-title":"International Conference on Machine Learning. PMLR","author":"Longpre"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.findings-acl.146"},{"issue":"59","key":"ref38","first-page":"1","article-title":"Domain-adversarial training of neural networks","volume":"17","author":"Ganin","year":"2016","journal-title":"Journal of Machine Learning Research"},{"key":"ref39","first-page":"1180","article-title":"Unsupervised domain adaptation by backpropagation","volume-title":"International Conference on Machine Learning.","author":"Ganin"},{"key":"ref40","article-title":"GPT-4o system card","author":"Hurst","year":"2024","journal-title":"arXiv preprint arXiv:2410.21276"},{"key":"ref41","article-title":"Decoupled weight decay regularization","volume-title":"International Conference on Learning Representations","author":"Loshchilov"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP48485.2024.10448173"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/SMC54092.2024.10831218"},{"issue":"11","key":"ref44","article-title":"Visualizing data using t-SNE","volume":"9","author":"Van der Maaten","year":"2008","journal-title":"Journal of Machine Learning Research"}],"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\/11434633.pdf?arnumber=11434633","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,3]],"date-time":"2026-04-03T04:57:31Z","timestamp":1775192251000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11434633\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,12,6]]},"references-count":44,"URL":"https:\/\/doi.org\/10.1109\/asru65441.2025.11434633","relation":{},"subject":[],"published":{"date-parts":[[2025,12,6]]}}}