{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,15]],"date-time":"2026-01-15T23:15:42Z","timestamp":1768518942219,"version":"3.49.0"},"reference-count":42,"publisher":"IEEE","license":[{"start":{"date-parts":[[2023,12,16]],"date-time":"2023-12-16T00:00:00Z","timestamp":1702684800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,12,16]],"date-time":"2023-12-16T00:00:00Z","timestamp":1702684800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100004721","name":"University of Tokyo","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100004721","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2023,12,16]]},"DOI":"10.1109\/asru57964.2023.10389693","type":"proceedings-article","created":{"date-parts":[[2024,1,19]],"date-time":"2024-01-19T18:38:40Z","timestamp":1705689520000},"page":"1-8","source":"Crossref","is-referenced-by-count":5,"title":["COCO-NUT: Corpus of Japanese Utterance and Voice Characteristics Description for Prompt-Based Control"],"prefix":"10.1109","author":[{"given":"Aya","family":"Watanabe","sequence":"first","affiliation":[{"name":"The University of Tokyo,Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Shinnosuke","family":"Takamichi","sequence":"additional","affiliation":[{"name":"The University of Tokyo,Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yuki","family":"Saito","sequence":"additional","affiliation":[{"name":"The University of Tokyo,Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Wataru","family":"Nakata","sequence":"additional","affiliation":[{"name":"The University of Tokyo,Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Detai","family":"Xin","sequence":"additional","affiliation":[{"name":"The University of Tokyo,Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hiroshi","family":"Saruwatari","sequence":"additional","affiliation":[{"name":"The University of Tokyo,Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1587\/transinf.2017EDP7165"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9747345"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10097113"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.21437\/SSW.2021-9"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2019-2668"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-1236"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2010-595"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-2861"},{"key":"ref9","article-title":"Zero-shot text-to-image generation","author":"Ramesh","year":"2021","journal-title":"arXiv:2102.12092"},{"key":"ref10","article-title":"CLAP: Learning audio concepts from natural language supervision","author":"Elizalde","year":"2022","journal-title":"arXiv:2206.04769"},{"key":"ref11","article-title":"MuLan: A joint embedding of music audio and natural language","author":"Huang","year":"2022","journal-title":"arXiv:2208.12415"},{"key":"ref12","article-title":"Imagen Video: High definition video generation with diffusion models","author":"Ho","year":"2022","journal-title":"arXiv:2210.02303"},{"key":"ref13","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"Proceedings of the 38th International Conference on Machine Learning","volume":"139","author":"Radford"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2441"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1250\/ast.41.761"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1405.0312"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P18-1238"},{"key":"ref18","article-title":"Audiocaps: Generating captions for audios in the wild","volume-title":"NAACL-HLT","author":"Kim"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9052990"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/icassp49357.2023.10095969"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10096285"},{"key":"ref22","article-title":"InstructTTS: Modelling expressive TTS in discrete latent space with natural language style prompt","author":"Yang","year":"2023","journal-title":"arXiv:2301.13662"},{"key":"ref23","article-title":"MusicLM: Generating music from text","author":"Agostinelli","year":"2023","journal-title":"arXiv:2301.11325"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10096517"},{"key":"ref25","volume-title":"LAION-Audio-630K","author":"Wu","year":"2022"},{"key":"ref26","article-title":"Dreamix: Video diffusion models are general video editors","author":"Molad","year":"2023","journal-title":"arXiv:2302.01329"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-1965"},{"key":"ref28","article-title":"JTubeSpeech: corpus of Japanese speech collected from YouTube for speech recognition and speaker verification","author":"Takamichi","year":"2021","journal-title":"arXiv:2112.09323"},{"key":"ref29","article-title":"ReazonSpeech: A free and massive corpus for Japanese ASR","volume-title":"Annual meetings of the Association for Natural Language Processing","author":"Yue Yin"},{"key":"ref30","article-title":"Bert: Pre-training of deep bidirectional transformers for language understanding","author":"Devlin","year":"2018","journal-title":"arXiv preprint arXiv:1810.04805"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461471"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2021-299"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1080\/01621459.1963.10500845"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461375"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9413815"},{"key":"ref36","article-title":"Robust speech recognition via large-scale weak supervision","author":"Radford","year":"2022","journal-title":"arXiv preprint arXiv:2212.04356"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.acl-main.240"},{"key":"ref38","article-title":"Audiocaps: Generating captions for audios in the wild","volume-title":"NAACL-HLT","author":"Kim"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/icassp49357.2023.10095969"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9746312"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3122291"},{"key":"ref42","article-title":"Roberta: A robustly optimized bert pretraining approach","author":"Liu","year":"2019","journal-title":"arXiv preprint arXiv:1907.11692"}],"event":{"name":"2023 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","location":"Taipei, Taiwan","start":{"date-parts":[[2023,12,16]]},"end":{"date-parts":[[2023,12,20]]}},"container-title":["2023 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/10388490\/10389614\/10389693.pdf?arnumber=10389693","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,1,23]],"date-time":"2024-01-23T16:36:09Z","timestamp":1706027769000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10389693\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,12,16]]},"references-count":42,"URL":"https:\/\/doi.org\/10.1109\/asru57964.2023.10389693","relation":{},"subject":[],"published":{"date-parts":[[2023,12,16]]}}}