{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,15]],"date-time":"2026-07-15T17:35:13Z","timestamp":1784136913374,"version":"3.55.0"},"reference-count":32,"publisher":"IEEE","license":[{"start":{"date-parts":[[2019,5,1]],"date-time":"2019-05-01T00:00:00Z","timestamp":1556668800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2019,5,1]],"date-time":"2019-05-01T00:00:00Z","timestamp":1556668800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2019,5,1]],"date-time":"2019-05-01T00:00:00Z","timestamp":1556668800000},"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":[[2019,5]]},"DOI":"10.1109\/icassp.2019.8682816","type":"proceedings-article","created":{"date-parts":[[2019,4,17]],"date-time":"2019-04-17T20:01:56Z","timestamp":1555531316000},"page":"6161-6165","source":"Crossref","is-referenced-by-count":25,"title":["Multi-speaker Sequence-to-sequence Speech Synthesis for Data Augmentation in Acoustic-to-word Speech Recognition"],"prefix":"10.1109","author":[{"given":"Sei","family":"Ueno","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Masato","family":"Mimura","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Shinsuke","family":"Sakai","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Tatsuya","family":"Kawahara","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref32","article-title":"JSUT corpus: free large-scale Japanese speech corpus for end-to-end speech synthesis","author":"sonobe","year":"2017","journal-title":"arXiv preprint 1711 00354"},{"key":"ref31","article-title":"Automatic differentiation in PyTorch","author":"paszke","year":"2017","journal-title":"NIPS-W"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.308"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1160"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/SLT.2018.8639589"},{"key":"ref12","first-page":"2962","article-title":"Deep voice 2: Multi-speaker neural text-to-speech","author":"gibiansky","year":"2017","journal-title":"Proc NIPS"},{"key":"ref13","first-page":"4779","article-title":"Natural TTS synthesis by conditioning WaveNet on mel spectrogram predictions","author":"shen","year":"2017","journal-title":"Proc INTERSPEECH"},{"key":"ref14","article-title":"Deep voice 3: Scaling text-to-speech with convolutional sequence learning","author":"ping","year":"2018","journal-title":"Proc ICRL"},{"key":"ref15","article-title":"Close to human quality TTS with transformer","author":"li","year":"2018","journal-title":"arXiv preprint 1809 08895"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8462576"},{"key":"ref17","doi-asserted-by":"crossref","first-page":"523","DOI":"10.21437\/Interspeech.2017-343","article-title":"Towards better decoding and language model integration in sequence to sequence models","author":"chorowski","year":"2017","journal-title":"Proc INTERSPEECH"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8462682"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-2456"},{"key":"ref28","first-page":"1929","article-title":"Dropout: A simple way to prevent neural networks from overfitting","author":"srivastava","year":"2014","journal-title":"Journal of Machine Learning Research"},{"key":"ref4","first-page":"577","article-title":"Attention-based models for speech recognition","author":"chorowski","year":"2015","journal-title":"Advances in neural information processing systems"},{"key":"ref27","first-page":"1468","article-title":"Fast and accurate recurrent neural network acoustic models for speech recognition","author":"sak","year":"2015","journal-title":"InterSpeech"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU.2017.8268937"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2016.7472618"},{"key":"ref29","first-page":"1","article-title":"Adam: A method for stochastic opti-mization","author":"kingma","year":"2014","journal-title":"preprint arXiv 1412 6980"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2016.7472621"},{"key":"ref8","doi-asserted-by":"crossref","first-page":"959","DOI":"10.21437\/Interspeech.2017-546","article-title":"Direct acoustics-to-word models for English conversational speech recognition","author":"audhkhasi","year":"2017","journal-title":"Proc INTERSPEECH"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2016.7472641"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178778"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461361"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1145\/1143844.1143891"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1392"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1558"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU.2017.8268950"},{"key":"ref24","article-title":"Transfer learning from speaker verification to multispeaker text-to-speech synthesis","author":"jia","year":"2018","journal-title":"arXiv preprint 1806 04558"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1424"},{"key":"ref26","first-page":"947","article-title":"Spontaneous speech corpus of Japanese","author":"maekawa","year":"2000","journal-title":"LREC"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2016.7472652"}],"event":{"name":"ICASSP 2019 - 2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","location":"Brighton, United Kingdom","start":{"date-parts":[[2019,5,12]]},"end":{"date-parts":[[2019,5,17]]}},"container-title":["ICASSP 2019 - 2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/8671773\/8682151\/08682816.pdf?arnumber=8682816","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,7,15]],"date-time":"2022-07-15T03:12:40Z","timestamp":1657854760000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/8682816\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019,5]]},"references-count":32,"URL":"https:\/\/doi.org\/10.1109\/icassp.2019.8682816","relation":{},"subject":[],"published":{"date-parts":[[2019,5]]}}}