{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,9,8]],"date-time":"2024-09-08T13:27:03Z","timestamp":1725802023743},"reference-count":25,"publisher":"IEEE","license":[{"start":{"date-parts":[[2022,12,11]],"date-time":"2022-12-11T00:00:00Z","timestamp":1670716800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2022,12,11]],"date-time":"2022-12-11T00:00:00Z","timestamp":1670716800000},"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":[[2022,12,11]]},"DOI":"10.1109\/iscslp57327.2022.10038031","type":"proceedings-article","created":{"date-parts":[[2023,2,8]],"date-time":"2023-02-08T18:53:24Z","timestamp":1675882404000},"page":"448-452","source":"Crossref","is-referenced-by-count":1,"title":["Speaking style compensation on synthetic audio for robust keyword spotting"],"prefix":"10.1109","author":[{"given":"Houjun","family":"Huang","sequence":"first","affiliation":[{"name":"AISpeech Ltd,Suzhou,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"BYanmin","family":"Qian","sequence":"additional","affiliation":[{"name":"Shanghai Jiao Tong University,MoE Key Lab of Artificial Intelligence,AI Institute X-LANCE Lab,Department of Computer Science and Engineering,Shanghai,China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","article-title":"Hello edge: Keyword spotting on microcontrollers","author":"Zhang","year":"2017","journal-title":"arXiv preprint arXiv:1711.07128"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-1363"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-1058"},{"key":"ref4","article-title":"A neural attention model for speech command recognition","author":"de Andrade","year":"2018","journal-title":"arXiv preprint arXiv:1808.08929"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-1003"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053193"},{"article-title":"Training wake word detection with synthesized speech data on confusion words","volume-title":"arXiv preprint arXiv:2011.01460","author":"Jia","key":"ref7"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9413448"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9414471"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/SLT48900.2021.9383525"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9414550"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9414292"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-2537"},{"key":"ref14","first-page":"3171","article-title":"Fastspeech: Fast, robust and controllable text to speech","author":"Ren","year":"2019","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8682804"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1456"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461368"},{"key":"ref18","article-title":"Aishell-2: transforming mandarin asr research into industrial scale","author":"Du","year":"2018","journal-title":"arXiv preprint arXiv:1808.10583"},{"article-title":"The kaldi speech recognition toolkit","volume-title":"IEEE 2011 workshop on automatic speech recognition and understanding, no. CONF. IEEE Signal Processing Society","author":"Povey","key":"ref19"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2020-2650"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461375"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/APSIPAASC47483.2019.9023039"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9054423"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ICSDA.2017.8384449"},{"key":"ref25","article-title":"Musan: A music, speech, and noise corpus","author":"Snyder","year":"2015","journal-title":"arXiv preprint arXiv:1510.08484"}],"event":{"name":"2022 13th International Symposium on Chinese Spoken Language Processing (ISCSLP)","start":{"date-parts":[[2022,12,11]]},"location":"Singapore, Singapore","end":{"date-parts":[[2022,12,14]]}},"container-title":["2022 13th International Symposium on Chinese Spoken Language Processing (ISCSLP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/10037756\/10037573\/10038031.pdf?arnumber=10038031","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,2,13]],"date-time":"2024-02-13T14:00:18Z","timestamp":1707832818000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10038031\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,12,11]]},"references-count":25,"URL":"https:\/\/doi.org\/10.1109\/iscslp57327.2022.10038031","relation":{},"subject":[],"published":{"date-parts":[[2022,12,11]]}}}