{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,22]],"date-time":"2026-04-22T18:12:16Z","timestamp":1776881536511,"version":"3.51.2"},"reference-count":20,"publisher":"IEEE","license":[{"start":{"date-parts":[[2019,12,1]],"date-time":"2019-12-01T00:00:00Z","timestamp":1575158400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2019,12,1]],"date-time":"2019-12-01T00:00:00Z","timestamp":1575158400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2019,12,1]],"date-time":"2019-12-01T00:00:00Z","timestamp":1575158400000},"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":[[2019,12]]},"DOI":"10.1109\/asru46091.2019.9003990","type":"proceedings-article","created":{"date-parts":[[2020,2,21]],"date-time":"2020-02-21T07:01:33Z","timestamp":1582268493000},"page":"996-1002","source":"Crossref","is-referenced-by-count":72,"title":["Speech Recognition with Augmented Synthesized Speech"],"prefix":"10.1109","author":[{"given":"Andrew","family":"Rosenberg","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yu","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Bhuvana","family":"Ramabhadran","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ye","family":"Jia","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Pedro","family":"Moreno","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yonghui","family":"Wu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zelin","family":"Wu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU.2017.8268950"},{"key":"ref11","year":"2018","journal-title":"Machine speech chain with one-shot speaker adaptation"},{"key":"ref12","article-title":"Transfer learning from speaker verification to multispeaker text-to-speech synthesis","author":"jia","year":"2018","journal-title":"Advances in Neural Information Processing Systems (NIPS)"},{"key":"ref13","author":"graves","year":"2013","journal-title":"Generating Sequences with Recurrent Neural Networks"},{"key":"ref14","author":"hsu","year":"2018","journal-title":"Hi-erarchical generative modeling for controllable speech synthesis"},{"key":"ref15","author":"shen","year":"2019","journal-title":"Lingvo a Modular and Scalable Framework for Sequence-to-Sequence Modeling"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8462105"},{"key":"ref17","author":"chan","year":"2016","journal-title":"La-tent sequence decompositions"},{"key":"ref18","author":"kingma","year":"2014","journal-title":"Adam A method for stochastic optimization"},{"key":"ref19","author":"goyal","year":"2017","journal-title":"1 hour"},{"key":"ref4","article-title":"Efficient neural audio synthesis","author":"kalchbrenner","year":"2018","journal-title":"ICML"},{"key":"ref3","author":"li","year":"2018","journal-title":"Training neural speech recognition systems with synthetic speech augmentation"},{"key":"ref6","author":"cooper","year":"2019","journal-title":"Text-to-speech synthesis using found data for low-resource languages"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178831"},{"key":"ref8","author":"denes","year":"1963","journal-title":"The speech chain The physics and biology of spoken language bell telephone laboratories"},{"key":"ref7","author":"wang","year":"2018","journal-title":"Style tokens Unsupervised style modeling control and transfer in end-to-end speech synthesis"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178964"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461368"},{"key":"ref9","author":"denes","year":"1993","journal-title":"The Speech Chain"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-1203"}],"event":{"name":"2019 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","location":"SG, Singapore","start":{"date-parts":[[2019,12,14]]},"end":{"date-parts":[[2019,12,18]]}},"container-title":["2019 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/8985378\/9003727\/09003990.pdf?arnumber=9003990","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,7,18]],"date-time":"2022-07-18T14:44:17Z","timestamp":1658155457000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9003990\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019,12]]},"references-count":20,"URL":"https:\/\/doi.org\/10.1109\/asru46091.2019.9003990","relation":{},"subject":[],"published":{"date-parts":[[2019,12]]}}}