{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,22]],"date-time":"2026-04-22T20:33:32Z","timestamp":1776890012770,"version":"3.51.2"},"reference-count":28,"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\/501100000266","name":"Engineering and Physical Sciences Research Council","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100000266","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\/icassp49357.2023.10095729","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":8,"title":["Autovocoder: Fast Waveform Generation from a Learned Speech Representation Using Differentiable Digital Signal Processing"],"prefix":"10.1109","author":[{"given":"Jacob J","family":"Webber","sequence":"first","affiliation":[{"name":"University of Edinburgh,The Centre for Speech Technology Research,United Kingdom"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Cassia","family":"Valentini-Botinhao","sequence":"additional","affiliation":[{"name":"University of Edinburgh,The Centre for Speech Technology Research,United Kingdom"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Evelyn","family":"Williams","sequence":"additional","affiliation":[{"name":"University of Edinburgh,The Centre for Speech Technology Research,United Kingdom"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Gustav Eje","family":"Henter","sequence":"additional","affiliation":[{"name":"KTH Royal Institute of Technology,Division of Speech, Music, and Hearing,Stockholm,Sweden"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Simon","family":"King","sequence":"additional","affiliation":[{"name":"University of Edinburgh,The Centre for Speech Technology Research,United Kingdom"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-1018"},{"key":"ref12","first-page":"2410","article-title":"Efficient neural audio synthesis","volume":"80","author":"kalchbrenner","year":"2018","journal-title":"Proc ICML"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10094729"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9746713"},{"key":"ref11","first-page":"3918","article-title":"Parallel WaveNet: Fast high-fidelity speech synthesis","volume":"80","author":"van den oord","year":"2018","journal-title":"Proc ICML"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-314"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2019.2956145"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461368"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-489"},{"key":"ref16","article-title":"wav2vec 2.0: A framework for self-supervised learning of speech representations","author":"baevski","year":"2020","journal-title":"Proc NeurIPS"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2019.2938863"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-10797"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/TASSP.1984.1164317"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/TASSP.1983.1164178"},{"key":"ref26","first-page":"5530","article-title":"Conditional variational autoencoder with adversarial learning for end-to-end text-to-speech","author":"kim","year":"2021","journal-title":"Proc ICML"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.25080\/Majora-7b98e3ed-003"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3129994"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1145\/1390156.1390294"},{"key":"ref21","first-page":"8024","article-title":"PyTorch: An imperative style, high-performance deep learning library","author":"paszke","year":"2019","journal-title":"Proc NeurIPS"},{"key":"ref28","year":"2015","journal-title":"Method for the subjective assessment of intermediate quality levels of coding systems ITU Recommendation ITU-R BS 1534-3"},{"key":"ref27","author":"ito","year":"2017","journal-title":"The LJ speech dataset"},{"key":"ref8","article-title":"FastSpeech: Fast, robust and controllable text to speech","volume":"32","author":"ren","year":"2019","journal-title":"Proc NeurIPS"},{"key":"ref7","first-page":"6588","article-title":"FastPitch: Parallel text-to-speech with pitch prediction","author":"?a?cucki","year":"2021","journal-title":"Proc ICASSP"},{"key":"ref9","article-title":"WaveNet: A generative model for raw audio","author":"van den oord","year":"2016"},{"key":"ref4","first-page":"17 022","article-title":"HiFi-GAN: Generative adversarial networks for efficient and high fidelity speech synthesis","volume":"33","author":"kong","year":"2020","journal-title":"Proc NeurIPS"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8682804"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-1647"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9413727"}],"event":{"name":"ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","location":"Rhodes Island, Greece","start":{"date-parts":[[2023,6,4]]},"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\/10095729.pdf?arnumber=10095729","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,11,20]],"date-time":"2023-11-20T19:07:06Z","timestamp":1700507226000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10095729\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,6,4]]},"references-count":28,"URL":"https:\/\/doi.org\/10.1109\/icassp49357.2023.10095729","relation":{},"subject":[],"published":{"date-parts":[[2023,6,4]]}}}