{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,12]],"date-time":"2026-06-12T16:59:31Z","timestamp":1781283571104,"version":"3.54.1"},"reference-count":37,"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\/icassp43922.2022.9747728","type":"proceedings-article","created":{"date-parts":[[2022,4,27]],"date-time":"2022-04-27T19:50:34Z","timestamp":1651089034000},"page":"8447-8451","source":"Crossref","is-referenced-by-count":5,"title":["On the Interplay between Sparsity, Naturalness, Intelligibility, and Prosody in Speech Synthesis"],"prefix":"10.1109","author":[{"given":"Cheng-I Jeff","family":"Lai","sequence":"first","affiliation":[{"name":"MIT CSAIL,USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Erica","family":"Cooper","sequence":"additional","affiliation":[{"name":"National Institute of Informatics,Japan"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yang","family":"Zhang","sequence":"additional","affiliation":[{"name":"MIT-IBM Watson AI Lab,USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Shiyu","family":"Chang","sequence":"additional","affiliation":[{"name":"MIT-IBM Watson AI Lab,USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Kaizhi","family":"Qian","sequence":"additional","affiliation":[{"name":"MIT-IBM Watson AI Lab,USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yi-Lun","family":"Liao","sequence":"additional","affiliation":[{"name":"MIT CSAIL,USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yung-Sung","family":"Chuang","sequence":"additional","affiliation":[{"name":"MIT CSAIL,USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Alexander H.","family":"Liu","sequence":"additional","affiliation":[{"name":"MIT CSAIL,USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Junichi","family":"Yamagishi","sequence":"additional","affiliation":[{"name":"National Institute of Informatics,Japan"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"David","family":"Cox","sequence":"additional","affiliation":[{"name":"MIT-IBM Watson AI Lab,USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"James","family":"Glass","sequence":"additional","affiliation":[{"name":"MIT CSAIL,USA"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9414408"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461368"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33016706"},{"key":"ref30","article-title":"Parp: Prune, adjust and re-prune for self-supervised speech recognition","author":"lai","year":"2021","journal-title":"NeurIPS"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1016\/j.specom.2009.04.004"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178964"},{"key":"ref35","article-title":"The lj speech dataset","author":"ito","year":"2017"},{"key":"ref34","article-title":"wav2vec 2.0: A framework for self-supervised learning of speech representations","author":"baevski","year":"2020","journal-title":"NeurIPS"},{"key":"ref10","article-title":"Hifi-gan: Generative adversarial networks for efficient and high fidelity speech synthesis","author":"kong","year":"2020","journal-title":"NeurIPS"},{"key":"ref11","article-title":"Parallel wavenet: Fast high-fidelity speech synthesis","author":"oord","year":"2018","journal-title":"ICML"},{"key":"ref12","article-title":"Squeezewave: Extremely lightweight vocoders for on-device speech synthesis","author":"zhai","year":"2020","journal-title":"arXiv preprint arXiv 2001 11085"},{"key":"ref13","article-title":"Diffwave: A versatile diffusion model for audio synthesis","author":"kong","year":"2021","journal-title":"ICLRE"},{"key":"ref14","article-title":"Wavegrad: Estimating gradients for waveform generation","author":"chen","year":"2021","journal-title":"ICLRE"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053795"},{"key":"ref16","article-title":"Non-autoregressive neural text-to-speech","author":"peng","year":"2020","journal-title":"ICML"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9054484"},{"key":"ref18","article-title":"Melgan: Generative adversarial networks for conditional waveform synthesis","author":"kumar","year":"2019","journal-title":"NeurIPS"},{"key":"ref19","article-title":"Efficienttts: An efficient and high-quality text-to-speech architecture","author":"miao","year":"2021","journal-title":"ICML"},{"key":"ref28","article-title":"Optimizing speech recognition for the edge","author":"shangguan","year":"2019","journal-title":"arXiv preprint arXiv 1909 11324"},{"key":"ref4","article-title":"What is the state of neural network pruning?","author":"blalock","year":"2020","journal-title":"The Conference on Systems and Machine Learning"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2012.6288897"},{"key":"ref3","article-title":"The state of sparsity in deep neural networks","author":"gale","year":"2019","journal-title":"arXiv preprint arXiv 1902 10869"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8683143"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9414505"},{"key":"ref5","article-title":"Wavenet: A generative model for raw audio","author":"van den oord","year":"2016","journal-title":"arXiv preprint arXiv 1609 03286"},{"key":"ref8","article-title":"Waveflow: A compact flow-based model for raw audio","author":"ping","year":"2020","journal-title":"ICML"},{"key":"ref7","article-title":"Efficient neural audio synthesis","author":"kalchbrenner","year":"2018","journal-title":"ICML"},{"key":"ref2","article-title":"The lottery ticket hypothesis: Finding sparse, trainable neural networks","author":"frankle","year":"2019","journal-title":"ICLRE"},{"key":"ref9","article-title":"Clarinet: Parallel wave generation in end-to-end text-to-speech","author":"ping","year":"2019","journal-title":"ICLRE"},{"key":"ref1","article-title":"A survey on neural speech synthesis","author":"tan","year":"2021","journal-title":"arXiv preprint arXiv 2106 13112"},{"key":"ref20","article-title":"Fastspeech: Fast, robust and controllable text to speech","author":"ren","year":"2019","journal-title":"NeurIPS"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9414403"},{"key":"ref21","article-title":"Fastspeech 2: Fast and high-quality end-to-end text to speech","author":"ren","year":"2021","journal-title":"ICLRE"},{"key":"ref24","article-title":"Neural wave-shaping synthesis","author":"hayes","year":"2021","journal-title":"ISMIR"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-1897"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461974"},{"key":"ref25","article-title":"Ddsp: Differentiable digital signal processing","author":"engel","year":"2020","journal-title":"ICLRE"}],"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\/09747728.pdf?arnumber=9747728","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,8,22]],"date-time":"2022-08-22T20:13:51Z","timestamp":1661199231000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9747728\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,5,23]]},"references-count":37,"URL":"https:\/\/doi.org\/10.1109\/icassp43922.2022.9747728","relation":{},"subject":[],"published":{"date-parts":[[2022,5,23]]}}}