{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,11,24]],"date-time":"2025-11-24T21:42:41Z","timestamp":1764020561254,"version":"3.28.0"},"reference-count":26,"publisher":"IEEE","license":[{"start":{"date-parts":[[2022,5,23]],"date-time":"2022-05-23T00:00:00Z","timestamp":1653264000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2022,5,23]],"date-time":"2022-05-23T00:00:00Z","timestamp":1653264000000},"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":[[2022,5,23]]},"DOI":"10.1109\/icassp43922.2022.9746291","type":"proceedings-article","created":{"date-parts":[[2022,4,27]],"date-time":"2022-04-27T19:50:34Z","timestamp":1651089034000},"page":"8307-8311","source":"Crossref","is-referenced-by-count":8,"title":["Distribution Augmentation for Low-Resource Expressive Text-To-Speech"],"prefix":"10.1109","author":[{"given":"Mateusz","family":"Lajszczak","sequence":"first","affiliation":[{"name":"Alexa AI, Amazon,Cambridge"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Animesh","family":"Prasad","sequence":"additional","affiliation":[{"name":"Alexa AI, Amazon,Cambridge"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Arent","family":"Van Korlaar","sequence":"additional","affiliation":[{"name":"Alexa AI, Amazon,Cambridge"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Bajibabu","family":"Bollepalli","sequence":"additional","affiliation":[{"name":"Alexa AI, Amazon,Cambridge"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Antonio","family":"Bonafonte","sequence":"additional","affiliation":[{"name":"Alexa AI, Amazon,Cambridge"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Arnaud","family":"Joly","sequence":"additional","affiliation":[{"name":"Alexa AI, Amazon,Cambridge"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Marco","family":"Nicolis","sequence":"additional","affiliation":[{"name":"Alexa AI, Amazon,Cambridge"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Alexis","family":"Moinet","sequence":"additional","affiliation":[{"name":"Alexa AI, Amazon,Cambridge"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Thomas","family":"Drugman","sequence":"additional","affiliation":[{"name":"Alexa AI, Amazon,Cambridge"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Trevor","family":"Wood","sequence":"additional","affiliation":[{"name":"Alexa AI, Amazon,Cambridge"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Elena","family":"Sokolova","sequence":"additional","affiliation":[{"name":"Alexa AI, Amazon,Cambridge"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.findings-acl.307"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8683862"},{"key":"ref12","first-page":"2075","article-title":"End-to-end text-to-speech for low-resource languages by cross-lingual transfer learning","author":"tu","year":"2019","journal-title":"InterSpeech"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8682168"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-1251"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/SLT.2018.8639682"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053678"},{"key":"ref17","article-title":"Flowtron: an autoregressive flow-based generative network for text-to-speech synthesis","author":"valle","year":"2021","journal-title":"International Conference on Learning Representations"},{"key":"ref18","first-page":"252","article-title":"Expressive neural voice cloning","author":"neekhara","year":"2021","journal-title":"Asian Conference on Machine Learning"},{"key":"ref19","article-title":"Mathematical and computational aspects of lexicalized grammars","author":"schabes","year":"1990","journal-title":"PhD dissertation"},{"key":"ref4","first-page":"125","article-title":"Wavenet: A generative model for raw audio","author":"van den oord","year":"2016","journal-title":"IEE Workshop on Speech Synthesis"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1186\/s40537-019-0197-0"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461368"},{"key":"ref5","first-page":"3918","article-title":"Parallel wavenet: Fast high-fidelity speech synthesis","author":"oord","year":"2018","journal-title":"International Conference on Machine Learning"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9413466"},{"key":"ref7","first-page":"5006","article-title":"Distribution augmentation for generative modeling","author":"jun","year":"2020","journal-title":"International Conference on Machine Learning"},{"article-title":"The effectiveness of data augmentation in image classification using deep learning","year":"2017","author":"perez","key":"ref2"},{"key":"ref9","first-page":"96","article-title":"Non-Autoregressive TTS with Explicit Duration Modelling for Low-Resource Highly Expressive Speech","author":"shah","year":"2021","journal-title":"IEE Workshop on Speech Synthesis"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW50498.2020.00359"},{"key":"ref20","first-page":"3053","article-title":"Inducing tree-substitution grammars","volume":"11","author":"cohn","year":"2010","journal-title":"The Journal of Machine Learning Research"},{"article-title":"Non-attentive tacotron: Robust and controllable neural TTS synthesis including unsupervised duration modeling","year":"2020","author":"shen","key":"ref22"},{"key":"ref21","first-page":"577","article-title":"Attention-based models for speech recognition","author":"chorowski","year":"2015","journal-title":"Advances in Neural Information Processing Systems 28 Annual Conference on Neural Information Processing Systems"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-1599"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9414444"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P18-1249"},{"key":"ref25","article-title":"The kaldi speech recognition toolkit","author":"povey","year":"2011","journal-title":"Workshop on Automatic Speech Recognition and Understanding"}],"event":{"name":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","start":{"date-parts":[[2022,5,23]]},"location":"Singapore, Singapore","end":{"date-parts":[[2022,5,27]]}},"container-title":["ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9745891\/9746004\/09746291.pdf?arnumber=9746291","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,8,15]],"date-time":"2022-08-15T20:05:18Z","timestamp":1660593918000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9746291\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,5,23]]},"references-count":26,"URL":"https:\/\/doi.org\/10.1109\/icassp43922.2022.9746291","relation":{},"subject":[],"published":{"date-parts":[[2022,5,23]]}}}