{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,10]],"date-time":"2026-06-10T16:00:15Z","timestamp":1781107215067,"version":"3.54.1"},"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\/icassp39728.2021.9415120","type":"proceedings-article","created":{"date-parts":[[2021,5,13]],"date-time":"2021-05-13T19:53:45Z","timestamp":1620935625000},"page":"6478-6482","source":"Crossref","is-referenced-by-count":54,"title":["Generative Speech Coding with Predictive Variance Regularization"],"prefix":"10.1109","author":[{"given":"W. Bastiaan","family":"Kleijn","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Andrew","family":"Storus","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Michael","family":"Chinen","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Tom","family":"Denton","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Felicia S. C.","family":"Lim","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Alejandro","family":"Luebs","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jan","family":"Skoglund","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hengchin","family":"Yeh","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7179063"},{"key":"ref31","author":"valin","year":"2012","journal-title":"Definition of the Opus Audio Codec"},{"key":"ref30","article-title":"Noisy speech database for training speech enhancement algorithms and tts models","author":"valentini-botinhao","year":"2016","journal-title":"University of Edinburgh School of Informatics Centre for Speech Technology Research (CSTR) Tech Rep"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-1255"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053657"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053220"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.2307\/2345178"},{"key":"ref14","first-page":"2672","article-title":"Generative adversarial nets","author":"goodfellow","year":"2014","journal-title":"Advances in neural information processing systems"},{"key":"ref15","first-page":"271","article-title":"f-GAN: Training generative neural samplers using variational divergence minimization","author":"nowozin","year":"2016","journal-title":"Advances in neural information processing systems"},{"key":"ref16","article-title":"Wasserstein GAN","author":"arjovsky","year":"2017","journal-title":"arXiv preprint arXiv 1701 07875"},{"key":"ref17","first-page":"1718","article-title":"Generative moment matching networks","author":"li","year":"2015","journal-title":"International Conference on Machine Learning"},{"key":"ref18","first-page":"2203","article-title":"MMD GAN: Towards deeper understanding of moment matching network","author":"li","year":"2017","journal-title":"Advances in neural information processing systems"},{"key":"ref19","article-title":"FloWaveNet: A generative flow for raw audio","author":"kim","year":"2018","journal-title":"arXiv preprint arXiv 1811 02155"},{"key":"ref28","article-title":"To prune, or not to prune: exploring the efficacy of pruning for model compression","author":"zhu","year":"2017","journal-title":"arXiv preprint arXiv 1710 01878"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8683143"},{"key":"ref27","first-page":"486","article-title":"Freesound datasets: a platform for the creation of open audio datasets","author":"fonseca","year":"2017","journal-title":"Proc 18th Int Society Music Information Retrieval Conference (IS- MIR 2017)"},{"key":"ref3","first-page":"3918","article-title":"Parallel WaveNet: Fast high-fidelity speech synthesis","author":"oord","year":"2018","journal-title":"Int Conference on Machine Learning"},{"key":"ref6","article-title":"GANSynth: Adversarial neural audio synthesis","author":"engel","year":"2019","journal-title":"arXiv preprint arXiv 1902 05023"},{"key":"ref29","year":"1996","journal-title":"Recommendation ITU-T P 800 Methods for Subjective Determination of Transmission Quality"},{"key":"ref5","article-title":"Adversarial audio synthesis","author":"donahue","year":"2018","journal-title":"arXiv preprint arXiv 1802 00420"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8682435"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8462529"},{"key":"ref2","article-title":"Efficient neural audio synthesis","author":"kalchbrenner","year":"2018","journal-title":"arXiv preprint arXiv 1802 08908"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8683277"},{"key":"ref1","article-title":"Wavenet: A generative model for raw audio","author":"oord","year":"2016","journal-title":"arXiv preprint arXiv 1609 04802"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2019.2915167"},{"key":"ref22","author":"o\u2019shaughnessy","year":"1987","journal-title":"Speech Communications Human And Machine (IEEE)"},{"key":"ref21","doi-asserted-by":"crossref","first-page":"831","DOI":"10.1109\/ICASSP40776.2020.9053846","article-title":"Performance study of a convolutional time-domain audio separation network for real-time speech denoising","author":"sonning","year":"2020","journal-title":"2020 IEEE Int Conf Acoust Speech Signal Processing (ICASSP)"},{"key":"ref24","article-title":"CSR- I (WSJ0) Other","author":"garofolo","year":"2016","journal-title":"Harvard Dataverse Tech Rep"},{"key":"ref23","article-title":"Empirical evaluation of gated recurrent neural networks on sequence modeling","author":"chung","year":"2014","journal-title":"arXiv preprint arXiv 1412 3555"},{"key":"ref26","article-title":"Common voice: A massively-multilingual speech corpus","author":"ardila","year":"2019","journal-title":"arXiv preprint arXiv 1912 06670"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178964"}],"event":{"name":"ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","location":"Toronto, ON, Canada","start":{"date-parts":[[2021,6,6]]},"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\/09415120.pdf?arnumber=9415120","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,12,27]],"date-time":"2022-12-27T08:31:40Z","timestamp":1672129900000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9415120\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,6,6]]},"references-count":32,"URL":"https:\/\/doi.org\/10.1109\/icassp39728.2021.9415120","relation":{},"subject":[],"published":{"date-parts":[[2021,6,6]]}}}