{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,11]],"date-time":"2026-03-11T01:23:03Z","timestamp":1773192183840,"version":"3.50.1"},"reference-count":66,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2022,1,1]],"date-time":"2022-01-01T00:00:00Z","timestamp":1640995200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2022,1,1]],"date-time":"2022-01-01T00:00:00Z","timestamp":1640995200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2022,1,1]],"date-time":"2022-01-01T00:00:00Z","timestamp":1640995200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"National Key Research and Development Program of China","award":["2020AAA0108600"],"award-info":[{"award-number":["2020AAA0108600"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE\/ACM Trans. Audio Speech Lang. Process."],"published-print":{"date-parts":[[2022]]},"DOI":"10.1109\/taslp.2022.3145297","type":"journal-article","created":{"date-parts":[[2022,1,25]],"date-time":"2022-01-25T20:37:40Z","timestamp":1643143060000},"page":"646-658","source":"Crossref","is-referenced-by-count":17,"title":["Disentangling Style and Speaker Attributes for TTS Style Transfer"],"prefix":"10.1109","volume":"30","author":[{"given":"Xiaochun","family":"An","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Frank K.","family":"Soong","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8234-0823","authenticated-orcid":false,"given":"Lei","family":"Xie","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461368"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-1452"},{"key":"ref3","first-page":"1","article-title":"Deep voice 3: 2000-speaker neural text-to-speech","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Ping","year":"2018"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU46091.2019.9003949"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053436"},{"key":"ref6","first-page":"3104","article-title":"Sequence to sequence learning with neural networks","volume-title":"Proc. Conf. Neural Inf. Process. Syst.","author":"Sutskever","year":"2014"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1146\/annurev.neuro.26.041002.131047"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/APSIPAASC47483.2019.9023186"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/SLT.2018.8639682"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3076369"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/SLT48900.2021.9383524"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1113"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU46091.2019.9003859"},{"key":"ref14","first-page":"1","article-title":"Hierarchical generative modeling for controllable speech synthesis","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Hsu","year":"2019"},{"key":"ref15","first-page":"1","article-title":"Semi-supervised generative modeling for controllable speech synthesis","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Habib","year":"2020"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053520"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-979"},{"key":"ref18","first-page":"4693","article-title":"Towards end-to-end prosody transfer for expressive speech synthesis with tacotron","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Skerry-Ryan","year":"2018"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ISCSLP49672.2021.9362069"},{"key":"ref20","first-page":"5180","article-title":"Style tokens: Unsupervised style modeling, control and transfer in end-to-end speech synthesis","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Wang","year":"2018"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8683623"},{"key":"ref22","first-page":"1","article-title":"Multi-reference tacotron by intercross training for style disentangling, transfer and control in speech synthesis","volume-title":"Proc.\nINTERSPEECH","author":"Bian","year":"2019"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-2985"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-1407"},{"key":"ref25","first-page":"1","article-title":"Auto-encoding variational bayes","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Kingma","year":"2014"},{"key":"ref26","first-page":"1","article-title":"The deep weight prior","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Atanov","year":"2019"},{"key":"ref27","first-page":"4743","article-title":"Improving variational inference with inverse autoregressive flow","volume-title":"Proc. Conf. Neural Inf. Process. Syst.","author":"Kingma","year":"2016"},{"key":"ref28","first-page":"3915","article-title":"Parallel WaveNet: Fast high-fidelity speech synthesis","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Oord","year":"2018"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.3390\/app10010302"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053678"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461375"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8462665"},{"key":"ref33","first-page":"4485","article-title":"Transfer learning from speaker verification to multispeaker text-to-speech synthesis","volume-title":"Proc. Conf. Neural Inf. Process. Syst.","author":"Jia","year":"2018"},{"key":"ref34","first-page":"2962","article-title":"Deep voice 2: Multi-speaker neural text-to-speech","volume-title":"Proc. Conf. Neural Inf. Process. Syst.","author":"Gibiansky","year":"2017"},{"key":"ref35","first-page":"1","article-title":"Prosody transfer in neural text to speech using global pitch and loudness features","volume-title":"Proc. CoRR","author":"Gururani","year":"2019"},{"key":"ref36","first-page":"5998","article-title":"Attention is all you need","volume-title":"Proc. Conf. Neural Inf. Process. Syst.","author":"Vaswani","year":"2017"},{"key":"ref37","first-page":"2672","article-title":"Generative adversarial nets","volume-title":"Proc. Conf. Neural Inf. Process. Syst.","author":"Goodfellow","year":"2014"},{"key":"ref38","first-page":"7354","article-title":"Self-attention generative adversarial networks","volume-title":"Proc. Mach. Learn. Res.","author":"Zhang","year":"2019"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/k16-1002"},{"key":"ref40","first-page":"1","article-title":"$\\beta$-VAE: Learning basic visual concepts with a constrained variational framework","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Higgins","year":"2017"},{"key":"ref41","first-page":"1","article-title":"Understanding disentangling in $\\beta$-VAE","volume-title":"Proc. Conf. Neural Inf. Process. Syst.","author":"Burgess","year":"2016"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2017-349"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1613\/jair.1872"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-1255"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8682804"},{"key":"ref46","first-page":"1530","article-title":"Variational inference with normalizing flows","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Rezende","year":"2015"},{"key":"ref47","first-page":"1","article-title":"Sylvester normalizing flows for variational inference","volume-title":"Proc. Uncertainty Artif. Intell.","author":"Berg","year":"2018"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2713"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1929"},{"key":"ref50","first-page":"1","article-title":"The Kaldi speech recognition toolkit","volume-title":"Proc. IEEE Autom. Speech Recognit. Understanding Workshop","author":"Povey","year":"2011"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1769"},{"key":"ref52","first-page":"2773","article-title":"Grammar as a foreign language","volume-title":"Proc. Conf. Neural Inf. Process. Syst.","author":"Vinyals","year":"2015"},{"key":"ref53","first-page":"577","article-title":"Attention-based models for speech recognition","volume-title":"Proc. Conf. Neural Inf. Process. Syst.","author":"Chorowski","year":"2015"},{"key":"ref54","first-page":"1","article-title":"Googles neural machine translation system: Bridging the gap between human and machine translation","volume-title":"Proc. CoRR","author":"Wu","year":"2016"},{"key":"ref55","first-page":"5047","article-title":"Disentangling factors of variation in deep representations using adversarial training","volume-title":"Proc. Neural Inf. Process. Syst.","author":"Mathieu","year":"2016"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.244"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1016\/j.neunet.2021.03.005"},{"key":"ref58","first-page":"881","article-title":"Made: Masked autoencoder for distribution estimation","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Germain","year":"2015"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2176"},{"key":"ref60","first-page":"2410","article-title":"Efficient neural audio synthesis","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Kalchbrenner","year":"2018"},{"key":"ref61","volume-title":"An Introduction to the Psychology of Hearing","author":"Moore","year":"2012"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9414858"},{"issue":"11","key":"ref63","first-page":"2579","article-title":"Visualizing data using t-SNE","volume":"9","author":"Maaten","year":"2008","journal-title":"J. Mach. Learn. Res."},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-1980"},{"key":"ref65","first-page":"1","article-title":"Clova Baseline System for the Voxceleb Speaker Recognition Challenge 2020","volume-title":"Proc. INTERSPEECH","author":"Heo","year":"2020"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-1704"}],"container-title":["IEEE\/ACM Transactions on Audio, Speech, and Language Processing"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6570655\/9657755\/09693198.pdf?arnumber=9693198","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,1,13]],"date-time":"2024-01-13T22:32:13Z","timestamp":1705185133000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9693198\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022]]},"references-count":66,"URL":"https:\/\/doi.org\/10.1109\/taslp.2022.3145297","relation":{},"ISSN":["2329-9290","2329-9304"],"issn-type":[{"value":"2329-9290","type":"print"},{"value":"2329-9304","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022]]}}}