{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,30]],"date-time":"2026-05-30T03:50:29Z","timestamp":1780113029624,"version":"3.54.0"},"reference-count":42,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"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":["IEEE\/ACM Trans. Audio Speech Lang. Process."],"published-print":{"date-parts":[[2023]]},"DOI":"10.1109\/taslp.2023.3290423","type":"journal-article","created":{"date-parts":[[2023,6,28]],"date-time":"2023-06-28T17:27:04Z","timestamp":1687973224000},"page":"2548-2557","source":"Crossref","is-referenced-by-count":6,"title":["Unsupervised TTS Acoustic Modeling for TTS With Conditional Disentangled Sequential VAE"],"prefix":"10.1109","volume":"31","author":[{"given":"Jiachen","family":"Lian","sequence":"first","affiliation":[{"name":"Tencent AI Lab Bellevue, Bellevue, WA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3851-2357","authenticated-orcid":false,"given":"Chunlei","family":"Zhang","sequence":"additional","affiliation":[{"name":"Tencent AI Lab Bellevue, Bellevue, WA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Gopala K.","family":"Anumanchipalli","sequence":"additional","affiliation":[{"name":"EECS, UC Berkeley, Berkeley, CA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0520-6844","authenticated-orcid":false,"given":"Dong","family":"Yu","sequence":"additional","affiliation":[{"name":"Tencent AI Lab Bellevue, Bellevue, WA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9747272"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-1386"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-11225"},{"key":"ref34","article-title":"Improving zero-shot voice style transfer via disentangled representation learning","author":"yuan","year":"0","journal-title":"Proc Int Conf Learn Representations"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2441"},{"key":"ref37","first-page":"1027","article-title":"K-means++: The advantages of careful seeding","author":"arthur","year":"0","journal-title":"Proc 18th Annu ACM-SIAM Symp Discrete Algorithms"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.7488\/ds\/2645"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178964"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00657"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.1996.541101"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2022.3188113"},{"key":"ref33","first-page":"10105","article-title":"Contrastively disentangled sequential variational autoencoder","volume":"34","author":"bai","year":"0","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3122291"},{"key":"ref32","article-title":"Disentangled recurrent wasserstein autoencoder","author":"han","year":"0","journal-title":"Proc Int Conf Learn Representations"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-2968"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-1452"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-414"},{"key":"ref39","first-page":"17022","article-title":"Hifi-gan: Generative adversarial networks for efficient and high fidelity speech synthesis","volume":"33","author":"kong","year":"0","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref16","article-title":"WaveNet: A generative model for raw","author":"oord","year":"2016"},{"key":"ref38","article-title":"Adam: A method for stochastic optimization","author":"kingma","year":"0","journal-title":"Proc Int Conf Learn Representations"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-11071"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-10294"},{"key":"ref24","first-page":"5670","article-title":"Disentangled sequential autoencoder","author":"yingzhen","year":"0","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref23","first-page":"1876","article-title":"Unsupervised learning of disentangled and interpretable representations from sequential data","volume":"30","author":"hsu","year":"0","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref26","first-page":"5210","article-title":"Autovc: Zero-shot voice style transfer with only autoencoder loss","author":"qian","year":"0","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-475"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-816"},{"key":"ref42","first-page":"6840","article-title":"Denoising diffusion probabilistic models","volume":"33","author":"ho","year":"0","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2018.2831456"},{"key":"ref22","article-title":"Towards end-to-end unsupervised speech recognition","author":"liu","year":"2022"},{"key":"ref21","first-page":"27826","article-title":"Unsupervised speech recognition","volume":"34","author":"baevski","year":"0","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9054057"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2022.3198315"},{"key":"ref29","first-page":"4485","article-title":"Transfer learning from speaker verification to multispeaker text-to-speech synthesis","volume":"31","author":"jia","year":"0","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref8","first-page":"5530","article-title":"Conditional variational autoencoder with adversarial learning for end-to-end text-to-speech","author":"kim","year":"0","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461368"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-10294"},{"key":"ref4","article-title":"Fastspeech 2: Fast and high-quality end-to-end text to speech","author":"ren","year":"0","journal-title":"Proc Int Conf Learn Representations"},{"key":"ref3","article-title":"Fastspeech: Fast, robust and controllable text to speech","volume":"32","author":"ren","year":"0","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref6","first-page":"8067","article-title":"Glow-tts: A generative flow for text-to-speech via monotonic alignment search","volume":"33","author":"kim","year":"0","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9413880"},{"key":"ref40","first-page":"2579","article-title":"Visualizing data using t-SNE","volume":"9","author":"maaten","year":"2008","journal-title":"J Mach Learn Res"}],"container-title":["IEEE\/ACM Transactions on Audio, Speech, and Language Processing"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6570655\/9970249\/10167841.pdf?arnumber=10167841","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,7,31]],"date-time":"2023-07-31T17:40:53Z","timestamp":1690825253000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10167841\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023]]},"references-count":42,"URL":"https:\/\/doi.org\/10.1109\/taslp.2023.3290423","relation":{},"ISSN":["2329-9290","2329-9304"],"issn-type":[{"value":"2329-9290","type":"print"},{"value":"2329-9304","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023]]}}}