{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,30]],"date-time":"2026-04-30T17:17:21Z","timestamp":1777569441076,"version":"3.51.4"},"reference-count":22,"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\/icassp43922.2022.9747236","type":"proceedings-article","created":{"date-parts":[[2022,4,27]],"date-time":"2022-04-27T19:50:34Z","timestamp":1651089034000},"page":"6982-6986","source":"Crossref","is-referenced-by-count":84,"title":["Torchaudio: Building Blocks for Audio and Speech Processing"],"prefix":"10.1109","author":[{"given":"Yao-Yuan","family":"Yang","sequence":"first","affiliation":[{"name":"University of California,San Diego"}]},{"given":"Moto","family":"Hira","sequence":"additional","affiliation":[{"name":"Meta AI"}]},{"given":"Zhaoheng","family":"Ni","sequence":"additional","affiliation":[{"name":"Meta AI"}]},{"given":"Artyom","family":"Astafurov","sequence":"additional","affiliation":[{"name":"Meta AI"}]},{"given":"Caroline","family":"Chen","sequence":"additional","affiliation":[{"name":"Meta AI"}]},{"given":"Christian","family":"Puhrsch","sequence":"additional","affiliation":[{"name":"Meta AI"}]},{"given":"David","family":"Pollack","sequence":"additional","affiliation":[{"name":"Solvemate Gmbh"}]},{"given":"Dmitriy","family":"Genzel","sequence":"additional","affiliation":[{"name":"Meta AI"}]},{"given":"Donny","family":"Greenberg","sequence":"additional","affiliation":[{"name":"Meta AI"}]},{"given":"Edward Z.","family":"Yang","sequence":"additional","affiliation":[{"name":"Meta AI"}]},{"given":"Jason","family":"Lian","sequence":"additional","affiliation":[{"name":"Meta AI"}]},{"given":"Jeff","family":"Hwang","sequence":"additional","affiliation":[{"name":"Meta AI"}]},{"given":"Ji","family":"Chen","sequence":"additional","affiliation":[{"name":"Meta AI"}]},{"given":"Peter","family":"Goldsborough","sequence":"additional","affiliation":[{"name":"Anduril Industries"}]},{"given":"Sean","family":"Narenthiran","sequence":"additional","affiliation":[{"name":"Grid AI Labs"}]},{"given":"Shinji","family":"Watanabe","sequence":"additional","affiliation":[{"name":"Carnegie Mellon University"}]},{"given":"Soumith","family":"Chintala","sequence":"additional","affiliation":[{"name":"Meta AI"}]},{"given":"Vincent","family":"Quenneville-Belair","sequence":"additional","affiliation":[{"name":"Meta AI"}]}],"member":"263","reference":[{"key":"ref10","article-title":"Nemo: a toolkit for building ai applications using neural modules","author":"kuchaiev","year":"2019"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8683713"},{"key":"ref12","article-title":"Speechbrain: A general-purpose speech toolkit","author":"ravanelli","year":"2021"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461368"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178964"},{"key":"ref15","article-title":"Cstr vctk corpus: English multi-speaker corpus for cstr voice cloning toolkit (version 0.92)","author":"yamagishi","year":"2019"},{"key":"ref16","article-title":"The lj speech dataset","author":"ito","year":"2017"},{"key":"ref17","article-title":"Deep speech: Scaling up end-to-end speech recognition","author":"hannun","year":"2014"},{"key":"ref18","article-title":"Wav2letter: an end-to-end convnet-based speech recognition system","author":"collobert","year":"2016"},{"key":"ref19","article-title":"wav2vec 2.0: A framework for self-supervised learning of speech representations","volume":"33","author":"baevski","year":"2020","journal-title":"Advances in neural information processing systems"},{"key":"ref4","doi-asserted-by":"crossref","first-page":"18","DOI":"10.25080\/Majora-7b98e3ed-003","article-title":"librosa: Audio and music signal analysis in python","volume":"8","author":"mcfee","year":"2015","journal-title":"Proceedings of the 14th Python in Science Conference"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1038\/s41586-020-2649-2"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-1673"},{"key":"ref5","article-title":"Ddsp: Differentiable digital signal processing","author":"engel","year":"2020","journal-title":"International Conference on Learning Representations"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU46091.2019.9003968"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1456"},{"key":"ref2","first-page":"8024","article-title":"Pytorch: An imperative style, high-performance deep learning library","author":"paszke","year":"2019","journal-title":"Advances in Neural IInformation Processing Systems"},{"key":"ref1","article-title":"TensorFlow: Large-scale machine learning on heterogeneous systems","author":"abadi","year":"2015"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/N19-4009"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2019.2915167"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8683143"},{"key":"ref21","first-page":"2410","article-title":"Efficient neural audio synthesis","author":"kalchbrenner","year":"2018","journal-title":"International Conference on Machine Learning"}],"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\/09747236.pdf?arnumber=9747236","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,8,15]],"date-time":"2022-08-15T20:07:16Z","timestamp":1660594036000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9747236\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,5,23]]},"references-count":22,"URL":"https:\/\/doi.org\/10.1109\/icassp43922.2022.9747236","relation":{},"subject":[],"published":{"date-parts":[[2022,5,23]]}}}