{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,15]],"date-time":"2026-05-15T02:14:30Z","timestamp":1778811270206,"version":"3.51.4"},"reference-count":38,"publisher":"IEEE","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2018,12]]},"DOI":"10.1109\/slt.2018.8639589","type":"proceedings-article","created":{"date-parts":[[2019,2,14]],"date-time":"2019-02-14T23:36:34Z","timestamp":1550187394000},"page":"477-484","source":"Crossref","is-referenced-by-count":32,"title":["Leveraging Sequence-to-Sequence Speech Synthesis for Enhancing Acoustic-to-Word Speech Recognition"],"prefix":"10.1109","author":[{"given":"Masato","family":"Mimura","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Sei","family":"Ueno","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hirofumi","family":"Inaguma","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Shinsuke","family":"Sakai","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Tatsuya","family":"Kawahara","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref38","article-title":"Listening while speaking: Speech chain by deep learning","author":"tjandra","year":"2017","journal-title":"ASRU"},{"key":"ref33","first-page":"1171","article-title":"Scheduled sampling for sequence prediction with recurrent neural networks","author":"bengio","year":"2015","journal-title":"NIPS"},{"key":"ref32","article-title":"Adam: A method for stochastic optimization","author":"kingma","year":"2014","journal-title":"arXiv preprint arXiv 1412 6980"},{"key":"ref31","first-page":"1929","article-title":"Dropout: A simple way to prevent neural networks from overfitting","volume":"15","author":"srivastava","year":"2014","journal-title":"Journal of Machine Learning Research"},{"key":"ref30","first-page":"7","article-title":"Corpus of Spontaneous Japanese: Its design and evaluation","author":"maekawa","year":"2003","journal-title":"Proc ISCA & IEEE Workshop on Spontaneous Speech Processing and Recognition"},{"key":"ref37","article-title":"Zoneout: Regularizing RNNs by randomly preserving hidden activations","author":"krueger","year":"2017","journal-title":"LCLR"},{"key":"ref36","article-title":"JSUT corpus: free large-scale japanese speech corpus for end-to-end speech synthesis","author":"sonobe","year":"2017","journal-title":"arXiv preprint arXiv 1711 03890"},{"key":"ref35","author":"paszke","year":"2017","journal-title":"On Automatic Differentiation"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.308"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2016.7472621"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2016.7472618"},{"key":"ref12","first-page":"4945","article-title":"Sequence transduction with recurrent neural networks","author":"graves","year":"2012","journal-title":"LCML"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2013.6638947"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-546"},{"key":"ref15","doi-asserted-by":"crossref","first-page":"3707","DOI":"10.21437\/Interspeech.2017-1566","article-title":"Neural speech recognizer: Acoustic-to-word LSTM model for large vocabulary speech recognition","author":"soltau","year":"2017","journal-title":"InterSpeech"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8462576"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1160"},{"key":"ref18","doi-asserted-by":"crossref","first-page":"4006","DOI":"10.21437\/Interspeech.2017-1452","article-title":"Tacotron: Towards end-to-end speech synthesis","author":"wang","year":"2017","journal-title":"InterSpeech"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461368"},{"key":"ref28","article-title":"Multi-level language modeling and decoding for open vocabulary end-to-end speech recognition","author":"hori","year":"2017","journal-title":"ASRU"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1145\/1143844.1143891"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-343"},{"key":"ref3","article-title":"English conversational telephone speech recognition by humans and machines","author":"saon","year":"2017","journal-title":"arXiv preprint arXiv 1703 06870"},{"key":"ref6","article-title":"Fast and accurate recurrent neural network acoustic models for speech recognition","author":"sak","year":"2015","journal-title":"arXiv preprint arXiv 1607 06947"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8462682"},{"key":"ref5","first-page":"1764","article-title":"Towards end-to-end speech recognition with recurrent neural networks","author":"graves","year":"2014","journal-title":"Proc 31st Int Conf Mach Learn"},{"key":"ref8","article-title":"End-to- end continuous speech recognition using attention-based recurrent NN: first results","author":"chorowski","year":"2014","journal-title":"Deep Learning and Representation Learning Workshop NIPS"},{"key":"ref7","first-page":"604","article-title":"Acoustic modelling with CD-CTC-SMBR LSTM RNNs","author":"sak","year":"2015","journal-title":"ASRU"},{"key":"ref2","article-title":"Achieving human parity in conversational speech recognition","author":"xiong","year":"2016","journal-title":"arXiv preprint arXiv 1610 0525"},{"key":"ref9","first-page":"577","article-title":"Attention-based models for speech recognition","author":"chorowski","year":"2015","journal-title":"Advances in Neural Information Processing Systems (NIPS)"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/MSP.2012.2205597"},{"key":"ref20","article-title":"Deep voice 3: Scaling text-to-speech with convolutional sequence learning","author":"ping","year":"2018","journal-title":"ICLRE"},{"key":"ref22","article-title":"Char2wav: End-to-end speech synthesis","author":"sotelo","year":"2017","journal-title":"ICLRE"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1997.9.8.1735"},{"key":"ref24","article-title":"Acoustic-to-word model without OOV","author":"li","year":"2017","journal-title":"ASRU"},{"key":"ref23","first-page":"448","article-title":"Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift","author":"ioffe","year":"2015","journal-title":"Proceedings of ICML"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1424"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461361"}],"event":{"name":"2018 IEEE Spoken Language Technology Workshop (SLT)","location":"Athens, Greece","start":{"date-parts":[[2018,12,18]]},"end":{"date-parts":[[2018,12,21]]}},"container-title":["2018 IEEE Spoken Language Technology Workshop (SLT)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/8632666\/8639030\/08639589.pdf?arnumber=8639589","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,1,27]],"date-time":"2022-01-27T08:26:15Z","timestamp":1643271975000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/8639589\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2018,12]]},"references-count":38,"URL":"https:\/\/doi.org\/10.1109\/slt.2018.8639589","relation":{},"subject":[],"published":{"date-parts":[[2018,12]]}}}