{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,7,20]],"date-time":"2025-07-20T03:55:52Z","timestamp":1752983752224},"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\/icassp43922.2022.9746202","type":"proceedings-article","created":{"date-parts":[[2022,4,27]],"date-time":"2022-04-27T19:50:34Z","timestamp":1651089034000},"page":"7467-7471","source":"Crossref","is-referenced-by-count":1,"title":["PAMA-TTS: Progression-Aware Monotonic Attention for Stable SEQ2SEQ TTS with Accurate Phoneme Duration Control"],"prefix":"10.1109","author":[{"given":"Yunchao","family":"He","sequence":"first","affiliation":[{"name":"Xiaomi Corporation,Beijing,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jian","family":"Luan","sequence":"additional","affiliation":[{"name":"Xiaomi Corporation,Beijing,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yujun","family":"Wang","sequence":"additional","affiliation":[{"name":"Xiaomi Corporation,Beijing,China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"article-title":"Durian: Duration informed attention network for multimodal synthesis","year":"2019","author":"yu","key":"ref10"},{"article-title":"Nonattentive tacotron: Robust and controllable neural tts synthesis including unsupervised duration modeling","year":"2020","author":"shen","key":"ref11"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9414718"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU46091.2019.9003956"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9054119"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-2123"},{"article-title":"End-to-end adversarial text-to-speech","year":"2020","author":"donahue","key":"ref16"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-1461"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-2121"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2019.2914149"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33016706"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461368"},{"key":"ref6","first-page":"1293","article-title":"Robust sequenceto-sequence acoustic modeling with stepwise monotonic attention for neural tts","author":"he","year":"2019","journal-title":"Proc INTERSPEECH"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8462020"},{"key":"ref8","first-page":"3165","article-title":"Fastspeech: Fast, robust and controllable text to speech","author":"ren","year":"2019","journal-title":"Proc NeurIPS"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9054106"},{"key":"ref2","doi-asserted-by":"crossref","first-page":"4006","DOI":"10.21437\/Interspeech.2017-1452","article-title":"Tacotron: Towards end-to-end speech synthesis","author":"wang","year":"2017","journal-title":"Proc INTERSPEECH"},{"key":"ref1","first-page":"6000","article-title":"Attention is all you need","author":"vaswani","year":"2017","journal-title":"Proc NIPS"},{"article-title":"Fastspeech 2: Fast and high-quality end-toend text to speech","year":"2020","author":"ren","key":"ref9"},{"key":"ref20","article-title":"The kaldi speech recognition toolkit","author":"povey","year":"2011","journal-title":"2011 IEEE Workshop on Automatic Speech Recognition & Understanding"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8682804"}],"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\/09746202.pdf?arnumber=9746202","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,8,22]],"date-time":"2022-08-22T20:13:23Z","timestamp":1661199203000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9746202\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,5,23]]},"references-count":21,"URL":"https:\/\/doi.org\/10.1109\/icassp43922.2022.9746202","relation":{},"subject":[],"published":{"date-parts":[[2022,5,23]]}}}