{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,17]],"date-time":"2026-04-17T17:00:14Z","timestamp":1776445214198,"version":"3.51.2"},"reference-count":21,"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\/icassp43922.2022.9747707","type":"proceedings-article","created":{"date-parts":[[2022,4,27]],"date-time":"2022-04-27T19:50:34Z","timestamp":1651089034000},"page":"6092-6096","source":"Crossref","is-referenced-by-count":43,"title":["One TTS Alignment to Rule Them All"],"prefix":"10.1109","author":[{"given":"Rohan","family":"Badlani","sequence":"first","affiliation":[{"name":"NVIDIA,Santa Clara"}]},{"given":"Adrian","family":"Lancucki","sequence":"additional","affiliation":[{"name":"NVIDIA,Santa Clara"}]},{"given":"Kevin J.","family":"Shih","sequence":"additional","affiliation":[{"name":"NVIDIA,Santa Clara"}]},{"given":"Rafael","family":"Valle","sequence":"additional","affiliation":[{"name":"NVIDIA,Santa Clara"}]},{"given":"Wei","family":"Ping","sequence":"additional","affiliation":[{"name":"NVIDIA,Santa Clara"}]},{"given":"Bryan","family":"Catanzaro","sequence":"additional","affiliation":[{"name":"NVIDIA,Santa Clara"}]}],"member":"263","reference":[{"key":"ref10","doi-asserted-by":"crossref","DOI":"10.21437\/Interspeech.2017-1386","article-title":"Montreal forced aligner: Trainable text-speech alignment using kaldi","author":"mcauliffe","year":"2017","journal-title":"InterSpeech"},{"key":"ref11","first-page":"7586","article-title":"Non-autoregressive neural text-to-speech","author":"peng","year":"2020","journal-title":"International Conference on Machine Learning"},{"key":"ref12","article-title":"RAD-TTS: Parallel flow-based TTS with robust alignment learning and diverse synthesis","author":"shih","year":"2021","journal-title":"ICML Workshop on Invertible Neural Networks Normalizing Flows and Explicit Likelihood Models"},{"key":"ref13","article-title":"Efficiently trainable text-to-speech system based on deep convolutional networks with guided attention","volume":"abs 1710 8969","author":"tachibana","year":"2017","journal-title":"CoRR"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/5.18626"},{"key":"ref15","first-page":"369","author":"graves","year":"2006","journal-title":"Connectionist temporal classification labelling unsegmented sequence data with recurrent neural networks"},{"key":"ref16","article-title":"Attention-based models for speech recognition","volume":"abs 1506 7503","author":"chorowski","year":"2015","journal-title":"CoRR"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9054106"},{"key":"ref18","article-title":"The lj speech dataset","author":"ito","year":"2017"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/PACRIM.1993.407206"},{"key":"ref4","article-title":"Fastspeech 2: Fast and high-quality end-to-end text-to-speech","author":"ren","year":"2020"},{"key":"ref3","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":"ref6","first-page":"8067","article-title":"Glow-tts: A generative flow for text-to-speech via monotonic alignment search","volume":"33","author":"kim","year":"2020","journal-title":"Advances in neural information processing systems"},{"key":"ref5","first-page":"3171","article-title":"Fastspeech: Fast, robust and controllable text to speech","volume":"32","author":"ren","year":"2019","journal-title":"Advances in neural information processing systems"},{"key":"ref8","article-title":"Generating sequences with recurrent neural networks","volume":"abs 1308 850","author":"graves","year":"2013","journal-title":"CoRR"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9413889"},{"key":"ref2","article-title":"Natural TTS synthesis by conditioning wavenet on mel spectrogram predictions","volume":"abs 1712 5884","author":"shen","year":"2017","journal-title":"CoRR"},{"key":"ref1","article-title":"Tacotron: A fully end-to-end text-to-speech synthesis model","volume":"abs 1703 10135","author":"wang","year":"2017","journal-title":"CoRR"},{"key":"ref9","article-title":"Neural machine translation by jointly learning to align and translate","author":"bahdanau","year":"2014"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2441"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-1819"}],"event":{"name":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","location":"Singapore, Singapore","start":{"date-parts":[[2022,5,23]]},"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\/09747707.pdf?arnumber=9747707","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,8,15]],"date-time":"2022-08-15T20:10:11Z","timestamp":1660594211000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9747707\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,5,23]]},"references-count":21,"URL":"https:\/\/doi.org\/10.1109\/icassp43922.2022.9747707","relation":{},"subject":[],"published":{"date-parts":[[2022,5,23]]}}}