{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,22]],"date-time":"2026-04-22T18:58:32Z","timestamp":1776884312216,"version":"3.51.2"},"reference-count":30,"publisher":"IEEE","license":[{"start":{"date-parts":[[2019,5,1]],"date-time":"2019-05-01T00:00:00Z","timestamp":1556668800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2019,5,1]],"date-time":"2019-05-01T00:00:00Z","timestamp":1556668800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2019,5,1]],"date-time":"2019-05-01T00:00:00Z","timestamp":1556668800000},"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":[[2019,5]]},"DOI":"10.1109\/icassp.2019.8683561","type":"proceedings-article","created":{"date-parts":[[2019,4,17]],"date-time":"2019-04-17T20:01:56Z","timestamp":1555531316000},"page":"5901-5905","source":"Crossref","is-referenced-by-count":57,"title":["Disentangling Correlated Speaker and Noise for Speech Synthesis via Data Augmentation and Adversarial Factorization"],"prefix":"10.1109","author":[{"given":"Wei-Ning","family":"Hsu","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yu","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ron J.","family":"Weiss","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yu-An","family":"Chung","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yuxuan","family":"Wang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yonghui","family":"Wu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"James","family":"Glass","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2016.7472652"},{"key":"ref10","article-title":"beta-VAE: Learning basic visual concepts with a constrained variational framework","author":"higgins","year":"2017","journal-title":"International Conference on Learning Representations (ICLR)"},{"key":"ref11","article-title":"CSTR VCTK Corpus: English multi-speaker corpus for CSTR voice cloning toolkit","author":"veaux","year":"2017"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1016\/j.csl.2016.11.005"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461368"},{"key":"ref14","article-title":"Auto-encoding variational Bayes","author":"kingma","year":"2014","journal-title":"International Conference on Learning Representations (ICLR)"},{"key":"ref15","first-page":"2096","article-title":"Domain-adversarial training of neural networks","volume":"17","author":"ganin","year":"2016","journal-title":"J Machine Learning Research (JMLR)"},{"key":"ref16","article-title":"Analysis of representations for domain adaptation","author":"ben-david","year":"2006","journal-title":"Advances in Neural Information Processing Systems (NIPS)"},{"key":"ref17","doi-asserted-by":"crossref","DOI":"10.21437\/Interspeech.2017-1510","article-title":"Generation of large-scale simulated utterances in virtual rooms to train deep-neural networks for far-field speech recognition in Google Home","author":"kim","year":"2017","journal-title":"InterSpeech"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU.2017.8268911"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2016.11.063"},{"key":"ref28","article-title":"Robust signal-to-noise ratio estimation based on waveform amplitude distribution analysis","author":"kim","year":"2008","journal-title":"InterSpeech"},{"key":"ref4","article-title":"Towards end-to-end prosody transfer for expressive speech synthesis with Tacotron","author":"skerry-ryan","year":"2018","journal-title":"International Conference on Machine Learning (ICML)"},{"key":"ref27","article-title":"Adam: A method for stochastic optimization","author":"kingma","year":"2015","journal-title":"International Conference on Learning Representations (ICLR)"},{"key":"ref3","article-title":"Style tokens: Unsupervised style modeling, control and transfer in end-to-end speech synthesis","author":"wang","year":"2018","journal-title":"International Conference on Machine Learning (ICML)"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1113"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8462665"},{"key":"ref5","article-title":"Transfer learning from speaker verification to multispeaker text-to-speech synthesis","author":"jia","year":"2018","journal-title":"Advances in Neural Information Processing Systems (NIPS)"},{"key":"ref8","article-title":"Hierarchical generative modeling for controllable speech synthesis","author":"hsu","year":"2018"},{"key":"ref7","article-title":"Deep encoder-decoder models for unsupervised learning of controllable speech synthesis","author":"henter","year":"2018"},{"key":"ref2","article-title":"Deep Voice 2: Multi-speaker neural text-to-speech","author":"arik","year":"2017","journal-title":"Advances in Neural Information Processing Systems (NIPS)"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178964"},{"key":"ref1","doi-asserted-by":"crossref","DOI":"10.21437\/Interspeech.2017-1452","article-title":"Tacotron: Towards end-to-end speech synthesis","author":"wang","year":"2017","journal-title":"InterSpeech"},{"key":"ref20","article-title":"Aurora working group: DSR front end LVCSR evaluation au\/384\/02","author":"pearce","year":"2002","journal-title":"Inst Signal Inform Process Mississippi State Univ"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8462663"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461932"},{"key":"ref24","article-title":"Disentangled sequential autoencoder","author":"yingzhen","year":"2018","journal-title":"International Conference on Machine Learning (ICML)"},{"key":"ref23","article-title":"Unsupervised learning of disentangled and interpretable representations from sequential data","author":"hsu","year":"2017","journal-title":"Advances in Neural Information Processing Systems (NIPS)"},{"key":"ref26","article-title":"Disentangling factors of variation in deep representation using adversarial training","author":"mathieu","year":"2016","journal-title":"Advances in Neural Information Processing Systems (NIPS)"},{"key":"ref25","article-title":"The variational fair autoencoder","author":"louizos","year":"2016","journal-title":"International Conference on Learning Representations (ICLR)"}],"event":{"name":"ICASSP 2019 - 2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","location":"Brighton, United Kingdom","start":{"date-parts":[[2019,5,12]]},"end":{"date-parts":[[2019,5,17]]}},"container-title":["ICASSP 2019 - 2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/8671773\/8682151\/08683561.pdf?arnumber=8683561","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,7,15]],"date-time":"2022-07-15T03:12:40Z","timestamp":1657854760000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/8683561\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019,5]]},"references-count":30,"URL":"https:\/\/doi.org\/10.1109\/icassp.2019.8683561","relation":{},"subject":[],"published":{"date-parts":[[2019,5]]}}}