{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,27]],"date-time":"2026-02-27T23:45:02Z","timestamp":1772235902800,"version":"3.50.1"},"reference-count":21,"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\/icassp39728.2021.9414605","type":"proceedings-article","created":{"date-parts":[[2021,5,13]],"date-time":"2021-05-13T19:53:45Z","timestamp":1620935625000},"page":"711-715","source":"Crossref","is-referenced-by-count":20,"title":["Enhancing into the Codec: Noise Robust Speech Coding with Vector-Quantized Autoencoders"],"prefix":"10.1109","author":[{"given":"Jonah","family":"Casebeer","sequence":"first","affiliation":[]},{"given":"Vinjai","family":"Vale","sequence":"additional","affiliation":[]},{"given":"Umut","family":"Isik","sequence":"additional","affiliation":[]},{"given":"Jean-Marc","family":"Valin","sequence":"additional","affiliation":[]},{"given":"Ritwik","family":"Giri","sequence":"additional","affiliation":[]},{"given":"Arvindh","family":"Krishnaswamy","sequence":"additional","affiliation":[]}],"member":"263","reference":[{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2019.2938863"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-1785"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053657"},{"key":"ref13","first-page":"3444","article-title":"Speech enhancement with weighted denoising auto-encoder","author":"xia","year":"2013","journal-title":"InterSpeech"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2014.2364452"},{"key":"ref15","doi-asserted-by":"crossref","first-page":"91","DOI":"10.1007\/978-3-319-22482-4_11","article-title":"Speech enhancement with lstm recurrent neural networks and its application to noise-robust asr","author":"weninger","year":"2015","journal-title":"International Conference on Latent Variable Analysis and Signal Separation"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-3027"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/MMSP.2018.8547084"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178964"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7952261"},{"key":"ref4","article-title":"Wavenet: A generative model for raw audio","author":"van den oord","year":"2016"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-1255"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8682804"},{"key":"ref5","article-title":"Towards achieving robust universal neural vocoding","author":"lorenzo-trueba","year":"2018"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/LSP.2020.3039765"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8683277"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8462529"},{"key":"ref1","article-title":"Definition of the opus audio codec","author":"valin","year":"2012","journal-title":"IETF"},{"key":"ref9","first-page":"6306","article-title":"Neural discrete representation learning","author":"van den oord","year":"2017","journal-title":"Advances in neural information processing systems"},{"key":"ref20","author":"valentini-botinhao","year":"2017","journal-title":"Noisy speech database for training speech enhancement algorithms and tts models"},{"key":"ref21","year":"2018","journal-title":"Recommendation P 808 Subjective evaluation of speech quality with a crowdsourcing approach"}],"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\/09414605.pdf?arnumber=9414605","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,5,10]],"date-time":"2022-05-10T15:40:59Z","timestamp":1652197259000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9414605\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,6,6]]},"references-count":21,"URL":"https:\/\/doi.org\/10.1109\/icassp39728.2021.9414605","relation":{},"subject":[],"published":{"date-parts":[[2021,6,6]]}}}