{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,8,7]],"date-time":"2025-08-07T21:03:39Z","timestamp":1754600619876,"version":"3.37.3"},"reference-count":27,"publisher":"IEEE","license":[{"start":{"date-parts":[[2023,6,4]],"date-time":"2023-06-04T00:00:00Z","timestamp":1685836800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,6,4]],"date-time":"2023-06-04T00:00:00Z","timestamp":1685836800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100004472","name":"Riksbankens Jubileumsfond","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100004472","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2023,6,4]]},"DOI":"10.1109\/icasspw59220.2023.10193157","type":"proceedings-article","created":{"date-parts":[[2023,8,2]],"date-time":"2023-08-02T17:30:54Z","timestamp":1690997454000},"page":"1-5","source":"Crossref","is-referenced-by-count":4,"title":["A Comparative Study of Self-Supervised Speech Representations in Read and Spontaneous TTS"],"prefix":"10.1109","author":[{"given":"Siyang","family":"Wang","sequence":"first","affiliation":[{"name":"KTH Royal Institute of Technology,Division of Speech, Music and Hearing,Stockholm,Sweden"}]},{"given":"Gustav Eje","family":"Henter","sequence":"additional","affiliation":[{"name":"KTH Royal Institute of Technology,Division of Speech, Music and Hearing,Stockholm,Sweden"}]},{"given":"Joakim","family":"Gustafson","sequence":"additional","affiliation":[{"name":"KTH Royal Institute of Technology,Division of Speech, Music and Hearing,Stockholm,Sweden"}]},{"given":"\u00c9va","family":"Sz\u00e9kely","sequence":"additional","affiliation":[{"name":"KTH Royal Institute of Technology,Division of Speech, Music and Hearing,Stockholm,Sweden"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-10797"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-489"},{"article-title":"HierSpeech: Bridging the gap between text and speech by hierarchical variational inference using self-supervised representations for speech synthesis","volume-title":"Proc. NeurIPS","author":"Lee","key":"ref3"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2021-1775"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-1873"},{"key":"ref6","first-page":"12449","article-title":"wav2vec 2.0: A framework for self-supervised learning of speech representations","volume-title":"Proc. NeurIPS","volume":"33","author":"Baevski"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3122291"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-475"},{"key":"ref9","first-page":"1336","article-title":"On generative spoken language modeling from raw audio","volume":"9","author":"Lakhotia","year":"2021","journal-title":"Transactions of the Association for Computational Linguistics"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9414776"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU51503.2021.9688093"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/slt54892.2023.10023428"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461368"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9413889"},{"article-title":"FastSpeech 2: Fast and high-quality end-to-end text to speech","volume-title":"Proc. ICLR","author":"Ren","key":"ref15"},{"key":"ref16","first-page":"8067","article-title":"Glow-TTS: A generative flow for text-to-speech via monotonic alignment search","volume-title":"Proc. NeurIPS","volume":"33","author":"Kim"},{"key":"ref17","first-page":"17022","article-title":"HiFi-GAN: Generative adversarial networks for efficient and high fidelity speech synthesis","volume-title":"Proc. NeurIPS","author":"Kong"},{"key":"ref18","article-title":"A survey on neural speech synthesis","volume-title":"arXiv preprint arXiv:2106.15561","author":"Tan","year":"2021"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.21437\/SSW.2019-44"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2836"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i11.26488"},{"volume-title":"The LJ Speech dataset","year":"2017","author":"Ito","key":"ref22"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1145\/3267851.3267898"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9054107"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9747707"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.21437\/SSW.2019-19"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9746395"}],"event":{"name":"2023 IEEE International Conference on Acoustics, Speech, and Signal Processing Workshops (ICASSPW)","start":{"date-parts":[[2023,6,4]]},"location":"Rhodes Island, Greece","end":{"date-parts":[[2023,6,10]]}},"container-title":["2023 IEEE International Conference on Acoustics, Speech, and Signal Processing Workshops (ICASSPW)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/10192576\/10192577\/10193157.pdf?arnumber=10193157","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,3,13]],"date-time":"2024-03-13T22:43:00Z","timestamp":1710369780000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10193157\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,6,4]]},"references-count":27,"URL":"https:\/\/doi.org\/10.1109\/icasspw59220.2023.10193157","relation":{},"subject":[],"published":{"date-parts":[[2023,6,4]]}}}