{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,22]],"date-time":"2026-04-22T20:17:54Z","timestamp":1776889074796,"version":"3.51.2"},"reference-count":60,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/legalcode"}],"funder":[{"DOI":"10.13039\/501100002241","name":"Japan Science and Technology Agency (JST) Support for Pioneering Research Initiated by the Next Generation","doi-asserted-by":"publisher","award":["JPMJSP2108"],"award-info":[{"award-number":["JPMJSP2108"]}],"id":[{"id":"10.13039\/501100002241","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001691","name":"Japan Society for the Promotion of Science (JSPS) Grants-in-Aid for Scientific Research","doi-asserted-by":"publisher","award":["JP23KJ0828"],"award-info":[{"award-number":["JP23KJ0828"]}],"id":[{"id":"10.13039\/501100001691","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001691","name":"Japan Society for the Promotion of Science (JSPS) Grants-in-Aid for Scientific Research","doi-asserted-by":"publisher","award":["21H04900"],"award-info":[{"award-number":["21H04900"]}],"id":[{"id":"10.13039\/501100001691","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001691","name":"Japan Society for the Promotion of Science (JSPS) Grants-in-Aid for Scientific Research","doi-asserted-by":"publisher","award":["22H03639"],"award-info":[{"award-number":["22H03639"]}],"id":[{"id":"10.13039\/501100001691","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001691","name":"Japan Society for the Promotion of Science (JSPS) Grants-in-Aid for Scientific Research","doi-asserted-by":"publisher","award":["21H05054"],"award-info":[{"award-number":["21H05054"]}],"id":[{"id":"10.13039\/501100001691","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100020963","name":"Moonshot Research and Development","doi-asserted-by":"publisher","award":["JPMJPS2011"],"award-info":[{"award-number":["JPMJPS2011"]}],"id":[{"id":"10.13039\/501100020963","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001691","name":"JST Fusion Oriented Research for disruptive Science and Technology","doi-asserted-by":"publisher","award":["JPMJFR226V"],"award-info":[{"award-number":["JPMJFR226V"]}],"id":[{"id":"10.13039\/501100001691","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Access"],"published-print":{"date-parts":[[2024]]},"DOI":"10.1109\/access.2024.3360885","type":"journal-article","created":{"date-parts":[[2024,2,1]],"date-time":"2024-02-01T18:48:40Z","timestamp":1706813320000},"page":"19752-19764","source":"Crossref","is-referenced-by-count":18,"title":["JVNV: A Corpus of Japanese Emotional Speech With Verbal Content and Nonverbal Expressions"],"prefix":"10.1109","volume":"12","author":[{"ORCID":"https:\/\/orcid.org\/0009-0007-1908-1137","authenticated-orcid":false,"given":"Detai","family":"Xin","sequence":"first","affiliation":[{"name":"Graduate School of Information Science and Technology, The University of Tokyo, Bunkyo, Tokyo, Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Junfeng","family":"Jiang","sequence":"additional","affiliation":[{"name":"Graduate School of Information Science and Technology, The University of Tokyo, Bunkyo, Tokyo, Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0520-7847","authenticated-orcid":false,"given":"Shinnosuke","family":"Takamichi","sequence":"additional","affiliation":[{"name":"Graduate School of Information Science and Technology, The University of Tokyo, Bunkyo, Tokyo, Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7967-2613","authenticated-orcid":false,"given":"Yuki","family":"Saito","sequence":"additional","affiliation":[{"name":"Graduate School of Information Science and Technology, The University of Tokyo, Bunkyo, Tokyo, Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6544-5076","authenticated-orcid":false,"given":"Akiko","family":"Aizawa","sequence":"additional","affiliation":[{"name":"National Institute of Informatics, Chiyoda, Tokyo, Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0876-5617","authenticated-orcid":false,"given":"Hiroshi","family":"Saruwatari","sequence":"additional","affiliation":[{"name":"Graduate School of Information Science and Technology, The University of Tokyo, Bunkyo, Tokyo, Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1093\/acprof:oso\/9780199250677.001.0001"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1007\/s10919-011-0115-4"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1007\/s10919-009-0070-5"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.4324\/9781351308724"},{"key":"ref5","first-page":"36","article-title":"Comparing non-verbal vocalisations in conversational speech corpora","volume-title":"Proc. LREC Workshop Corpora Res. Emotion Sentiment Social Signals","author":"Trouvain"},{"key":"ref6","first-page":"196","article-title":"Affect bursts","volume-title":"Emotions: Essays Emotion Theory","volume":"161","author":"Scherer","year":"1994"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.3758\/BRM.40.2.531"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1073\/pnas.0908239106"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.3758\/s13428-013-0324-3"},{"key":"ref10","article-title":"Exploring the effectiveness of self-supervised learning and classifier chains in emotion recognition of nonverbal vocalizations","volume-title":"Proc. ICML Expressive Vocalizations Workshop","author":"Xin"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.emnlp-main.769"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10096033"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2023-806"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10095294"},{"key":"ref15","article-title":"LaughNet: Synthesizing laughter utterances from waveform silhouettes and a single laughter example","author":"Luong","year":"2021","journal-title":"arXiv:2110.04946"},{"key":"ref16","article-title":"The emotional voices database: Towards controlling the emotion dimension in voice generation systems","author":"Adigwe","year":"2018","journal-title":"arXiv:1806.09514"},{"key":"ref17","first-page":"223","article-title":"The CMU Arctic speech databases","volume-title":"Proc. 5th ISCA Workshop Speech Synth.","author":"Kominek"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICSDA.2016.7918977"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-300"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1250\/ast.33.359"},{"key":"ref21","first-page":"584","article-title":"Learning sentiment of nouns from selectional preferences of verbs and adjectives","volume-title":"Proc. 14th Annu. Meeting Assoc. Natural Lang. Process.","author":"Higashiyama"},{"key":"ref22","doi-asserted-by":"crossref","DOI":"10.1016\/j.specom.2023.103004","article-title":"JNV corpus: A corpus of Japanese nonverbal vocalizations with diverse phrases and emotions","volume":"156","author":"Xin","year":"2024","journal-title":"Speech Commun."},{"key":"ref23","first-page":"207","article-title":"Universal and cultural differences in facial expression of emotion","volume-title":"Proc. Nebraska Symp. Motivat.","author":"Eckman"},{"key":"ref24","volume-title":"The LJ Speech Dataset","author":"Ito","year":"2017"},{"key":"ref25","volume-title":"Superseded-CSTR VCTK Corpus: English Multi-speaker Corpus for Cstr Voice Cloning Toolkit","author":"Veaux","year":"1028"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.21437\/Eurospeech.2001-255"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.21437\/Eurospeech.2003-118"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2006-397"},{"key":"ref29","first-page":"99","article-title":"Towards optimal TTS corpora","volume-title":"Proc. LREC","author":"Cadic"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2017.2688585"},{"issue":"8","key":"ref31","first-page":"9","article-title":"Language models are unsupervised multitask learners","volume":"1","author":"Radford","year":"2019","journal-title":"OpenAI Blog"},{"key":"ref32","article-title":"Emergent abilities of large language models","author":"Wei","year":"2022","journal-title":"Trans. Mach. Learn. Res."},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1016\/j.procs.2014.11.020"},{"key":"ref34","first-page":"1877","article-title":"Language models are few-shot learners","volume-title":"Proc. NeurIPS","volume":"33","author":"Brown"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1907.11692"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.naacl-main.169"},{"key":"ref37","first-page":"2699","article-title":"Masked language model scoring","volume-title":"Proc. 58th Annu. Meeting Assoc. Comput. Linguistics","author":"Salazar"},{"key":"ref38","first-page":"4171","article-title":"BERT: Pre-training of deep bidirectional transformers for language understanding","volume-title":"Proc. NAACL","author":"Devlin"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1016\/S0167-6393(02)00084-5"},{"key":"ref40","article-title":"Synthesizing personalized non-speech vocalization from discrete speech representations","author":"Hsu","year":"2022","journal-title":"arXiv:2206.12662"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3122291"},{"key":"ref42","article-title":"FastSpeech 2: Fast and high-quality end-to-end text to speech","volume-title":"Proc. ICLR","author":"Ren"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1145\/1143844.1143891"},{"key":"ref44","first-page":"8067","article-title":"Glow-TTS: A generative flow for text-to-speech via monotonic alignment search","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"33","author":"Kim"},{"key":"ref45","article-title":"JSUT corpus: Free large-scale Japanese speech corpus for end-to-end speech synthesis","author":"Sonobe","year":"2017","journal-title":"arXiv:1711.00354"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1587\/transinf.2015EDP7457"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178964"},{"key":"ref48","first-page":"1027","article-title":"K-means++: The advantages of careful seeding","volume-title":"Proc. 18th Annu. ACM-SIAM Symp. Discrete Algorithms","author":"Arthur"},{"key":"ref49","article-title":"Adam: A method for stochastic optimization","author":"Kingma","year":"2014","journal-title":"arXiv:1412.6980"},{"key":"ref50","article-title":"Attention is all you need","volume-title":"Proc. NeurIPS","volume":"30","author":"Vaswani"},{"key":"ref51","first-page":"17022","article-title":"HiFi-GAN: Generative adversarial networks for efficient and high fidelity speech synthesis","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"33","author":"Kong"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8682283"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-353"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1057\/s41599-020-0499-z"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/W19-5935"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2023.3285283"},{"key":"ref57","article-title":"Privacy against real-time speech emotion detection via acoustic adversarial evasion of machine learning","author":"Testa","year":"2022","journal-title":"arXiv:2211.09273"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1016\/B978-0-12-558701-3.50007-7"},{"key":"ref59","article-title":"PyTorch: An imperative style, high-performance deep learning library","volume-title":"Proc. NeurIPS","volume":"32","author":"Paszke"},{"key":"ref60","first-page":"38","article-title":"Transformers: State-of-the-art natural language processing","volume-title":"Proc. Conf. Empirical Methods Natural Lang. Syst. Demonstrations","author":"Wolf"}],"container-title":["IEEE Access"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6287639\/10380310\/10418504.pdf?arnumber=10418504","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,2,13]],"date-time":"2024-02-13T09:28:33Z","timestamp":1707816513000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10418504\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024]]},"references-count":60,"URL":"https:\/\/doi.org\/10.1109\/access.2024.3360885","relation":{},"ISSN":["2169-3536"],"issn-type":[{"value":"2169-3536","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024]]}}}