{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,10]],"date-time":"2026-05-10T07:15:08Z","timestamp":1778397308673,"version":"3.51.4"},"reference-count":37,"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\/icassp43922.2022.9746217","type":"proceedings-article","created":{"date-parts":[[2022,4,27]],"date-time":"2022-04-27T19:50:34Z","timestamp":1651089034000},"page":"7682-7686","source":"Crossref","is-referenced-by-count":26,"title":["SYNT++: Utilizing Imperfect Synthetic Data to Improve Speech Recognition"],"prefix":"10.1109","author":[{"given":"Ting-Yao","family":"Hu","sequence":"first","affiliation":[{"name":"Apple"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Mohammadreza","family":"Armandpour","sequence":"additional","affiliation":[{"name":"Texas A&M University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ashish","family":"Shrivastava","sequence":"additional","affiliation":[{"name":"Apple"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jen-Hao Rick","family":"Chang","sequence":"additional","affiliation":[{"name":"Apple"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hema","family":"Koppula","sequence":"additional","affiliation":[{"name":"Apple"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Oncel","family":"Tuzel","sequence":"additional","affiliation":[{"name":"Apple"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-3015"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1456"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2441"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178964"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9414797"},{"key":"ref36","article-title":"Speech Commands: A Dataset for Limited-Vocabulary Speech Recognition","author":"warden","year":"2018"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2680"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33016706"},{"key":"ref10","article-title":"Fastspeech 2: Fast and high-quality end-to-end text to speech","author":"ren","year":"2021","journal-title":"Proc ICLR"},{"key":"ref11","article-title":"Deep voice 3: Scaling text-to-speech with convolutional sequence learning","author":"ping","year":"2018","journal-title":"Proc ICLR"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8683480"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-3167"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8683307"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/SLT.2018.8639619"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9413375"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053008"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053139"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU46091.2019.9003990"},{"key":"ref28","article-title":"Generative adversarial nets","author":"goodfellow","year":"2014","journal-title":"Proc NIPS"},{"key":"ref4","article-title":"Style tokens: Unsupervised style modeling, control and transfer in end-to-end speech synthesis","author":"wang","year":"2018","journal-title":"Proc ICML"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9054591"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00090"},{"key":"ref6","article-title":"Pattern recognition and machine learning","author":"bishop","year":"2007","journal-title":"Information Science and Statistics"},{"key":"ref29","article-title":"Batch normalization: Accelerating deep network training by reducing internal covariate shift","author":"ioffe","year":"2015","journal-title":"Proc ICML"},{"key":"ref5","article-title":"Style equalization: Unsupervised learning of controllable generative sequence models","author":"chang","year":"2021"},{"key":"ref8","article-title":"Variational rejection sampling","author":"grover","year":"2018","journal-title":"Proc AISTATS"},{"key":"ref7","article-title":"Discriminator rejection sampling","author":"azadi","year":"2019","journal-title":"Proc ICLR"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/K18-2025"},{"key":"ref1","article-title":"A generative adversarial network for style modeling in a text-to-speech system","author":"ma","year":"2019","journal-title":"ICLRE"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461368"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/SLT.2018.8639589"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9414778"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-1475"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053193"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9413448"},{"key":"ref26","article-title":"Data augmentation generative adversarial networks","author":"antoniou","year":"2017"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.241"}],"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\/09746217.pdf?arnumber=9746217","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,8,22]],"date-time":"2022-08-22T20:11:51Z","timestamp":1661199111000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9746217\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,5,23]]},"references-count":37,"URL":"https:\/\/doi.org\/10.1109\/icassp43922.2022.9746217","relation":{},"subject":[],"published":{"date-parts":[[2022,5,23]]}}}