{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,9,7]],"date-time":"2024-09-07T08:57:36Z","timestamp":1725699456949},"reference-count":32,"publisher":"IEEE","license":[{"start":{"date-parts":[[2021,6,6]],"date-time":"2021-06-06T00:00:00Z","timestamp":1622937600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2021,6,6]],"date-time":"2021-06-06T00:00:00Z","timestamp":1622937600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2021,6,6]],"date-time":"2021-06-06T00:00:00Z","timestamp":1622937600000},"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":[[2021,6,6]]},"DOI":"10.1109\/icassp39728.2021.9414870","type":"proceedings-article","created":{"date-parts":[[2021,5,13]],"date-time":"2021-05-13T19:53:45Z","timestamp":1620935625000},"page":"5714-5718","source":"Crossref","is-referenced-by-count":6,"title":["Fcl-Taco2: Towards Fast, Controllable and Lightweight Text-to-Speech Synthesis"],"prefix":"10.1109","author":[{"given":"Disong","family":"Wang","sequence":"first","affiliation":[]},{"given":"Liqun","family":"Deng","sequence":"additional","affiliation":[]},{"given":"Yang","family":"Zhang","sequence":"additional","affiliation":[]},{"given":"Nianzu","family":"Zheng","sequence":"additional","affiliation":[]},{"given":"Yu Ting","family":"Yeung","sequence":"additional","affiliation":[]},{"given":"Xiao","family":"Chen","sequence":"additional","affiliation":[]},{"given":"Xunying","family":"Liu","sequence":"additional","affiliation":[]},{"given":"Helen","family":"Meng","sequence":"additional","affiliation":[]}],"member":"263","reference":[{"article-title":"Adam: A method for stochastic optimization","year":"2014","author":"kingma","key":"ref32"},{"key":"ref31","first-page":"6199","article-title":"Parallel WaveGAN: A fast waveform generation model based on generative adversarial networks with multi-resolution spectrogram","author":"yamamoto","year":"2020","journal-title":"IEEE International Conference on Acoustics Speech and Signal Processing (ICASSP)"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1456"},{"article-title":"Deep voice 3: Scaling text-to-speech with convolutional sequence learning","year":"2017","author":"ping","key":"ref10"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33016706"},{"key":"ref12","first-page":"3171","article-title":"Fastspeech: Fast, robust and controllable text to speech","author":"ren","year":"2019","journal-title":"Advances in neural information processing systems"},{"article-title":"FastSpeech 2: Fast and High-Quality End-to-End Text-to-Speech","year":"2020","author":"ren","key":"ref13"},{"article-title":"Parallel neural text-to-speech","year":"2019","author":"peng","key":"ref14"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9054484"},{"article-title":"Glow-TTS: A Generative Flow for Text-to-Speech via Monotonic Alignment Search","year":"2020","author":"kim","key":"ref16"},{"key":"ref17","first-page":"6714","article-title":"Aligntts: Efficient feed-forward text-to-speech system without explicit alignment","author":"zeng","year":"2020","journal-title":"IEEE International Conference on Acoustics Speech and Signal Processing (ICASSP)"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-1976"},{"article-title":"TalkNet: Fully-Convolutional Non-Autoregressive Speech Synthesis Model","year":"2020","author":"beliaev","key":"ref19"},{"article-title":"Tinybert: Distilling bert for natural language understanding","year":"2019","author":"jiao","key":"ref28"},{"article-title":"SqueezeWave: Extremely Lightweight Vocoders for On-device Speech Synthesis","year":"2020","author":"zhai","key":"ref4"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.754"},{"article-title":"A real-time wideband neural vocoder at 1.6 kb\/s using LPCNet","year":"2019","author":"valin","key":"ref3"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2016-522"},{"article-title":"The lj speech dataset","year":"2017","author":"ito","key":"ref29"},{"article-title":"Fastwave: Accelerating autoregressive convolutional neural networks on fpga","year":"2020","author":"hussain","key":"ref5"},{"article-title":"Distilling the knowledge in a neural network","year":"2015","author":"hinton","key":"ref8"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461368"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/MSP.2014.2359987"},{"key":"ref9","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":"InterSpeech"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1631\/FITEE.1700826"},{"article-title":"FastPitch: Parallel Text-to-speech with Pitch Prediction","year":"2020","author":"?a?cucki","key":"ref20"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-1386"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-2867"},{"key":"ref24","first-page":"577","article-title":"Attention-based models for speech recognition","author":"chorowski","year":"2015","journal-title":"Advances in neural information processing systems"},{"article-title":"PPSpeech: Phrase based Parallel End-to-End TTS System","year":"2020","author":"cong","key":"ref23"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1997.9.8.1735"},{"key":"ref25","first-page":"1097","article-title":"Imagenet classification with deep convolutional neural networks","author":"krizhevsky","year":"2012","journal-title":"Advances in neural information processing systems"}],"event":{"name":"ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","start":{"date-parts":[[2021,6,6]]},"location":"Toronto, ON, Canada","end":{"date-parts":[[2021,6,11]]}},"container-title":["ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9413349\/9413350\/09414870.pdf?arnumber=9414870","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,5,10]],"date-time":"2022-05-10T15:40:56Z","timestamp":1652197256000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9414870\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,6,6]]},"references-count":32,"URL":"https:\/\/doi.org\/10.1109\/icassp39728.2021.9414870","relation":{},"subject":[],"published":{"date-parts":[[2021,6,6]]}}}