{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,1,29]],"date-time":"2025-01-29T05:28:21Z","timestamp":1738128501331,"version":"3.33.0"},"reference-count":32,"publisher":"IEEE","license":[{"start":{"date-parts":[[2024,12,3]],"date-time":"2024-12-03T00:00:00Z","timestamp":1733184000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,12,3]],"date-time":"2024-12-03T00:00:00Z","timestamp":1733184000000},"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":[[2024,12,3]]},"DOI":"10.1109\/apsipaasc63619.2025.10849285","type":"proceedings-article","created":{"date-parts":[[2025,1,27]],"date-time":"2025-01-27T18:37:05Z","timestamp":1738003025000},"page":"1-6","source":"Crossref","is-referenced-by-count":0,"title":["Enhancing Neural Speech Embeddings for Generative Speech Models"],"prefix":"10.1109","author":[{"given":"Doyeon","family":"Kim","sequence":"first","affiliation":[{"name":"Yonsei University,Dept. of Electrical and Electronic Eng.,Seoul,Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yanjue","family":"Song","sequence":"additional","affiliation":[{"name":"IDLab, Ghent University - imec,Ghent,Belgium"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Nilesh","family":"Madhu","sequence":"additional","affiliation":[{"name":"IDLab, Ghent University - imec,Ghent,Belgium"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hong-Goo","family":"Kang","sequence":"additional","affiliation":[{"name":"Yonsei University,Dept. of Electrical and Electronic Eng.,Seoul,Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","first-page":"12 449","article-title":"Wav2vec 2.0: A framework for self-supervised learning of speech representations","volume-title":"Proc. Adv. in Neural Inf. Process. Syst","volume":"33","author":"Baevski"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2022.3188113"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3122291"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2021-1775"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.23919\/APSIPAASC55919.2022.9980218"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-10002"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9746303"},{"article-title":"BigVGAN: A universal neural vocoder with large-scale training","volume-title":"Proc. Intl. Conf. on Telecommun. and Signal Process","author":"Lee","key":"ref8"},{"key":"ref9","article-title":"StyleTTS 2: Towards human-level text-to-speech through style diffusion and adversarial training with large speech language models","volume-title":"Proc. Adv. in Neural Inf. Process. Syst","volume":"36","author":"Li"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-1016"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10094705"},{"key":"ref12","first-page":"17 022","article-title":"HiFi-GAN: Generative adversarial networks for efficient and high fidelity speech synthesis","volume-title":"Proc. Adv. in Neural Inf. Process. Syst","volume":"33","author":"Kong"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP48485.2024.10447464"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/WASPAA58266.2023.10248089"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9747473"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/TSP52935.2021.9522648"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1007\/978-0-387-84858-7"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/iceic61013.2024.10457271"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3095662"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9414878"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1108\/RR-08-2013-0197"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7952261"},{"article-title":"Freesound datasets: A platform for the creation of open audio datasets","volume-title":"Proc. Intl. Soc. for Music Inf. Retrieval","author":"Fonseca","key":"ref23"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1121\/1.4799597"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7953152"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2021-1609"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1016\/0167-6393(93)90095-3"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1073\/pnas.1612524113"},{"article-title":"Decoupled weight decay regularization","volume-title":"Proc. Intl. Conf. on Learning Representations","author":"Loshchilov","key":"ref29"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-299"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.30420\/456164052"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2004-668"}],"event":{"name":"2024 Asia Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC)","start":{"date-parts":[[2024,12,3]]},"location":"Macau, Macao","end":{"date-parts":[[2024,12,6]]}},"container-title":["2024 Asia Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/10848542\/10848533\/10849285.pdf?arnumber=10849285","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,1,28]],"date-time":"2025-01-28T06:25:55Z","timestamp":1738045555000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10849285\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,12,3]]},"references-count":32,"URL":"https:\/\/doi.org\/10.1109\/apsipaasc63619.2025.10849285","relation":{},"subject":[],"published":{"date-parts":[[2024,12,3]]}}}