{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,11,29]],"date-time":"2025-11-29T07:20:58Z","timestamp":1764400858615,"version":"3.46.0"},"reference-count":23,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,10,22]],"date-time":"2025-10-22T00:00:00Z","timestamp":1761091200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,10,22]],"date-time":"2025-10-22T00:00:00Z","timestamp":1761091200000},"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":[[2025,10,22]]},"DOI":"10.1109\/apsipaasc65261.2025.11249207","type":"proceedings-article","created":{"date-parts":[[2025,11,28]],"date-time":"2025-11-28T18:40:26Z","timestamp":1764355226000},"page":"741-746","source":"Crossref","is-referenced-by-count":0,"title":["ASRQ-VC: ASR-Guided Speech Content Quantization for High-Fidelity Voice Conversion"],"prefix":"10.1109","author":[{"given":"Songting","family":"Liu","sequence":"first","affiliation":[{"name":"Nanyang Technological University,Singapore"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Deheng","family":"Ye","sequence":"additional","affiliation":[{"name":"Tencent Inc.,Singapore"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Wei","family":"Yang","sequence":"additional","affiliation":[{"name":"Tencent Inc.,Singapore"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Haoyang","family":"Li","sequence":"additional","affiliation":[{"name":"Nanyang Technological University,Singapore"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Eng Siong","family":"Chng","sequence":"additional","affiliation":[{"name":"Nanyang Technological University,Singapore"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3122291"},{"journal-title":"Vq-wav2vec: Self-supervised learning of discrete speech representations","year":"2019","author":"Baevski","key":"ref2"},{"key":"ref3","first-page":"18003","article-title":"Contentvec: An improved self-supervised speech representation by disentangling speakers","volume-title":"International Conference on Machine Learning","author":"Qian","year":"2022"},{"journal-title":"Cosyvoice: A scalable multilingual zero-shot text-to-speech synthesizer based on supervised semantic tokens","year":"2024","author":"Du","key":"ref4"},{"journal-title":"Finite scalar quantization: Vq-vae made simple","year":"2023","author":"Mentzer","key":"ref5"},{"key":"ref6","first-page":"5530","article-title":"Conditional variational autoencoder with adversarial learning for end-to-end text-to-speech","volume-title":"International Conference on Machine Learning","author":"Kim","year":"2021"},{"journal-title":"Vec2wav 2.0: Advancing voice conversion via discrete token vocoders","year":"2024","author":"Guo","key":"ref7"},{"key":"ref8","first-page":"5210","article-title":"Autovc: Zero-shot voice style transfer with only autoencoder loss","volume-title":"International Conference on Machine Learning","author":"Qian","year":"2019"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2022.3188113"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-475"},{"key":"ref11","first-page":"2709","article-title":"Yourtts: Towards zeroshot multi-speaker tts and zero-shot voice conversion for everyone","volume-title":"International Conference on Machine Learning","author":"Casanova","year":"2022"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10095191"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2023-1513"},{"key":"ref14","article-title":"Attention is all you need","author":"Vaswani","year":"2017","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-1965"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-2826"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52729.2023.01548"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2023.127063"},{"key":"ref19","article-title":"Root mean square layer normalization","volume":"32","author":"Zhang","year":"2019","journal-title":"Advances in Neural Information Processing Systems"},{"journal-title":"Glu variants improve transformer","year":"2020","author":"Shazeer","key":"ref20"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9746108"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2023-817"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i16.29740"}],"event":{"name":"2025 Asia Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC)","start":{"date-parts":[[2025,10,22]]},"location":"Singapore, Singapore","end":{"date-parts":[[2025,10,24]]}},"container-title":["2025 Asia Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11248853\/11248968\/11249207.pdf?arnumber=11249207","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,11,29]],"date-time":"2025-11-29T07:16:05Z","timestamp":1764400565000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11249207\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,22]]},"references-count":23,"URL":"https:\/\/doi.org\/10.1109\/apsipaasc65261.2025.11249207","relation":{},"subject":[],"published":{"date-parts":[[2025,10,22]]}}}