{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,2,21]],"date-time":"2025-02-21T01:36:28Z","timestamp":1740101788605,"version":"3.37.3"},"reference-count":22,"publisher":"IEEE","license":[{"start":{"date-parts":[[2023,6,4]],"date-time":"2023-06-04T00:00:00Z","timestamp":1685836800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,6,4]],"date-time":"2023-06-04T00:00:00Z","timestamp":1685836800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2023,6,4]]},"DOI":"10.1109\/icassp49357.2023.10095640","type":"proceedings-article","created":{"date-parts":[[2023,5,5]],"date-time":"2023-05-05T17:28:30Z","timestamp":1683307710000},"page":"1-5","source":"Crossref","is-referenced-by-count":0,"title":["VF-Taco2: Towards Fast and Lightweight Synthesis for Autoregressive Models with Variation Autoencoder and Feature Distillation"],"prefix":"10.1109","author":[{"given":"Yuhao","family":"Liu","sequence":"first","affiliation":[{"name":"Tianjin University,College of Intelligence and Computing,Tianjin Key Laboratory of Cognitive Computing and Application,Tianjin,China"}]},{"given":"Cheng","family":"Gong","sequence":"additional","affiliation":[{"name":"Tianjin University,College of Intelligence and Computing,Tianjin Key Laboratory of Cognitive Computing and Application,Tianjin,China"}]},{"given":"Longbiao","family":"Wang","sequence":"additional","affiliation":[{"name":"Tianjin University,College of Intelligence and Computing,Tianjin Key Laboratory of Cognitive Computing and Application,Tianjin,China"}]},{"given":"Xixin","family":"Wu","sequence":"additional","affiliation":[{"name":"The Chinese University of Hong Kong,HK SAR,China"}]},{"given":"Qiuyu","family":"Liu","sequence":"additional","affiliation":[{"name":"Tianjin University,College of Intelligence and Computing,Tianjin Key Laboratory of Cognitive Computing and Application,Tianjin,China"}]},{"given":"Jianwu","family":"Dang","sequence":"additional","affiliation":[{"name":"Tianjin University,College of Intelligence and Computing,Tianjin Key Laboratory of Cognitive Computing and Application,Tianjin,China"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461368"},{"key":"ref2","first-page":"3165","article-title":"Fastspeech: Fast, robust and controllable text to speech","volume-title":"Advances in Neural Information Processing Systems 32: Annual Conference on Neural Information Processing Systems 2019, NeurIPS 2019","author":"Ren"},{"article-title":"Fastspeech 2: Fast and high-quality end-toend text to speech","volume-title":"9th International Conference on Learning Representations, ICLR 2021","author":"Ren","key":"ref3"},{"key":"ref4","first-page":"141","article-title":"Parallel tacotron 2: A nonautoregressive neural TTS model with differentiable duration modeling","volume-title":"Interspeech 2021, 22nd Annual Conference of the International Speech Communication Association, Brno, Czechia, 30 August - 3 September 2021","author":"Elias"},{"key":"ref5","article-title":"Parallel synthesis for autoregressive speech generation","volume":"abs\/2204.11806","author":"Hsu","year":"2022","journal-title":"CoRR"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-1452"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-852"},{"article-title":"Auto-encoding variational bayes","year":"2013","author":"Kingma","key":"ref8"},{"key":"ref9","first-page":"2672","article-title":"Generative adversarial nets","volume-title":"Advances in Neural Information Processing Systems 27: Annual Conference on Neural Information Processing Systems 2014, December 8-13 2014","author":"Goodfellow"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053436"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1113"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8683623"},{"key":"ref13","article-title":"Distilling the knowledge in a neural network","author":"Hinton","year":"2015","journal-title":"arXiv preprint arXiv"},{"key":"ref14","article-title":"Binaryconnect: Training deep neural networks with binary weights during propagations","volume":"28","author":"Courbariaux","year":"2015","journal-title":"Advances in neural information processing systems"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.155"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8682804"},{"key":"ref17","article-title":"Squeeze-wave: Extremely lightweight vocoders for on-device speech synthesis","author":"Zhai","year":"2020","journal-title":"arXiv preprint arXiv:2001.05685"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2022.3171974"},{"key":"ref19","article-title":"Nix-tts: An incredibly lightweight end-to-end text-to-speech model via non end-to-end distillation","author":"Chevi","year":"2022","journal-title":"arXiv preprint arXiv:2203.15643"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9414870"},{"key":"ref21","article-title":"Contrastive learning rivals masked image modeling in fine-tuning via feature distillation","author":"Wei","year":"2022","journal-title":"arXiv preprint arXiv:2205.14141"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/APSIPAASC47483.2019.9023186"}],"event":{"name":"ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","start":{"date-parts":[[2023,6,4]]},"location":"Rhodes Island, Greece","end":{"date-parts":[[2023,6,10]]}},"container-title":["ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/10094559\/10094560\/10095640.pdf?arnumber=10095640","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,1,12]],"date-time":"2024-01-12T02:05:06Z","timestamp":1705025106000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10095640\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,6,4]]},"references-count":22,"URL":"https:\/\/doi.org\/10.1109\/icassp49357.2023.10095640","relation":{},"subject":[],"published":{"date-parts":[[2023,6,4]]}}}