{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,11,2]],"date-time":"2025-11-02T01:59:40Z","timestamp":1762048780430,"version":"build-2065373602"},"reference-count":33,"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\/icassp43922.2022.9746103","type":"proceedings-article","created":{"date-parts":[[2022,4,27]],"date-time":"2022-04-27T19:50:34Z","timestamp":1651089034000},"page":"8437-8441","source":"Crossref","is-referenced-by-count":5,"title":["Neural Speech Synthesis on a Shoestring: Improving the Efficiency of Lpcnet"],"prefix":"10.1109","author":[{"given":"Jean-Marc","family":"Valin","sequence":"first","affiliation":[{"name":"Amazon Web Services,Palo Alto,CA,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Umut","family":"Isik","sequence":"additional","affiliation":[{"name":"Amazon Web Services,Palo Alto,CA,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Paris","family":"Smaragdis","sequence":"additional","affiliation":[{"name":"Amazon Web Services,Palo Alto,CA,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Arvindh","family":"Krishnaswamy","sequence":"additional","affiliation":[{"name":"Amazon Web Services,Palo Alto,CA,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"journal-title":"Recommendation P 808 Subjective evaluation of speech quality with a crowdsourcing approach","year":"2018","key":"ref33"},{"journal-title":"Recommendation P 800 Methods for Subjective Determination of Transmission Quality","year":"1996","key":"ref32"},{"article-title":"The speex codec manual","year":"2007","author":"valin","key":"ref31"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2011-317"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8682804"},{"key":"ref11","article-title":"A real-time wideband neural vocoder at 1.6 kb\/s using LPCNet","author":"valin","year":"2019","journal-title":"Proc INTERSPEECH"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-1642"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-2041"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8462431"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/MMSP.2018.8547084"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1989.1.2.270"},{"key":"ref17","first-page":"1171","article-title":"Scheduled sampling for sequence prediction with recurrent neural networks","volume":"1","author":"bengio","year":"2015","journal-title":"Proc International Conference on Neural Information Processing Systems (NIPS)"},{"key":"ref18","article-title":"Sequence level training with recurrent neural networks","author":"ranzato","year":"2016","journal-title":"Proc ICLR"},{"key":"ref19","article-title":"Open-source Multi-speaker Corpora of the English Accents in the British Isles","author":"demirsahin","year":"2020","journal-title":"Proc LREC"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/LSP.2013.2249661"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2000.861820"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-1599"},{"article-title":"SampleRNN: An unconditional end-to-end neural audio generation model","year":"2016","author":"mehri","key":"ref3"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461368"},{"key":"ref29","article-title":"Adam: A method for stochastic optimization","author":"kingma","year":"2015","journal-title":"Proc ICLR"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.1996.541110"},{"key":"ref8","article-title":"Adversarial audio synthesis","author":"donahue","year":"2019","journal-title":"Proc ICLR"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8462529"},{"article-title":"Efficient neural audio synthesis","year":"2018","author":"kalchbrenner","key":"ref2"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8683143"},{"article-title":"WaveNet: A generative model for raw audio","year":"2016","author":"van den oord","key":"ref1"},{"key":"ref20","article-title":"Open-Source High Quality Speech Datasets for Basque, Catalan and Galician","author":"kjartansson","year":"2020","journal-title":"Proc SLTU and CCURL"},{"key":"ref22","article-title":"Crowdsourcing Latin American Spanish for Low-Resource Text-to-Speech","author":"guevara-rukoz","year":"2020","journal-title":"Proc LREC"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.21437\/SLTU.2018-14"},{"key":"ref24","article-title":"Burmese Speech Corpus, Finite-State Text Normalization and Pronunciation Grammars with an Application to Text-to-Speech","author":"oo","year":"2020","journal-title":"Proc LREC"},{"key":"ref23","article-title":"Open-source Multi-speaker Speech Corpora for Building Gujarati, Kannada, Malayalam, Marathi, Tamil and Telugu Speech Synthesis Systems","author":"he","year":"2020","journal-title":"Proc LREC"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-1096"},{"key":"ref25","doi-asserted-by":"crossref","DOI":"10.21437\/Interspeech.2017-1139","article-title":"Rapid development of TTS corpora for four South African languages","author":"van niekerk","year":"2017","journal-title":"Proc INTERSPEECH"}],"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\/09746103.pdf?arnumber=9746103","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,8,22]],"date-time":"2022-08-22T20:15:07Z","timestamp":1661199307000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9746103\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,5,23]]},"references-count":33,"URL":"https:\/\/doi.org\/10.1109\/icassp43922.2022.9746103","relation":{},"subject":[],"published":{"date-parts":[[2022,5,23]]}}}