{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,3]],"date-time":"2026-04-03T15:28:21Z","timestamp":1775230101732,"version":"3.50.1"},"reference-count":36,"publisher":"IEEE","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2017,12]]},"DOI":"10.1109\/asru.2017.8268950","type":"proceedings-article","created":{"date-parts":[[2018,1,25]],"date-time":"2018-01-25T21:43:53Z","timestamp":1516916633000},"page":"301-308","source":"Crossref","is-referenced-by-count":79,"title":["Listening while speaking: Speech chain by deep learning"],"prefix":"10.1109","author":[{"given":"Andros","family":"Tjandra","sequence":"first","affiliation":[]},{"given":"Sakriani","family":"Sakti","sequence":"additional","affiliation":[]},{"given":"Satoshi","family":"Nakamura","sequence":"additional","affiliation":[]}],"member":"263","reference":[{"key":"ref33","author":"cho","year":"2014","journal-title":"Learning phrase representations using RNN encoder-decoder for statistical machine translation"},{"key":"ref32","author":"xu","year":"2015","journal-title":"Empirical evaluation of rectified activations in convolutional network"},{"key":"ref31","article-title":"librosa 0.5.0","author":"mcfee","year":"2017"},{"key":"ref30","article-title":"Creating corpora for speech-to-speech translation","author":"kikui","year":"2003","journal-title":"Eighth European Conference on Speech Communication and Technology"},{"key":"ref36","author":"cheng","year":"2016","journal-title":"Semi-supervised learning for neural machine translation"},{"key":"ref35","first-page":"820","article-title":"Dual learning for machine translation","author":"di he","year":"2016","journal-title":"Advances in neural information processing systems"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1145\/2287710.2287712"},{"key":"ref10","doi-asserted-by":"crossref","first-page":"483","DOI":"10.21437\/ICSLP.1992-125","article-title":"Atr v-talk speech","author":"sagisaka","year":"1992","journal-title":"Proceedings of ICSLP"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.1996.541110"},{"key":"ref12","doi-asserted-by":"crossref","first-page":"2347","DOI":"10.21437\/Eurospeech.1999-513","article-title":"Simultaneous modeling of spectrum, pitch and duration in HMM - based speech synthesis","author":"yoshimura","year":"1999","journal-title":"Proceedings of EUROSPEECH"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.1995.479684"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2013.6638947"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178781"},{"key":"ref16","article-title":"Learning the speech front-end with raw waveform cldnns","volume":"2015","author":"sainath","year":"2015","journal-title":"InterSpeech"},{"key":"ref17","first-page":"7962","article-title":"Sta-tistical parametric speech synthesis using deep neural networks","author":"zen","year":"2013","journal-title":"Proceedings of the IEEE International Conference on Acoustics Speech and Signal Processing (ICASSP)"},{"key":"ref18","author":"oord","year":"2016","journal-title":"WaveNet A Generative Model for Raw Audio"},{"key":"ref19","author":"arik","year":"2017","journal-title":"Deep Voice Real-time neural text-to-speech"},{"key":"ref28","author":"graves","year":"2013","journal-title":"Generating Sequences with Recurrent Neural Networks"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TASSP.1978.1163055"},{"key":"ref27","author":"luong","year":"2015","journal-title":"Effective approaches to attention-based neural machine translation[J]"},{"key":"ref3","first-page":"81","article-title":"Speech discrimination by dynamic programming","author":"vintsyuk","year":"1968","journal-title":"Kibernetika"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/29.103088"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/TASSP.1984.1164317"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/PROC.1976.10159"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.1977.1170350"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1177\/002383096400700301"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1121\/1.1906946"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.1988.196677"},{"key":"ref1","author":"denes","year":"1993","journal-title":"The Speech Chain Anchor books"},{"key":"ref20","article-title":"National Research Council","year":"2004","journal-title":"Hearing Loss Determining Eligibility for Social Security Benefits"},{"key":"ref22","first-page":"3104","article-title":"Sequence-to-Sequence learning with neural networks","author":"sutskever","year":"2014","journal-title":"Advances in neural information processing systems"},{"key":"ref21","author":"bahdanau","year":"2014","journal-title":"Neural machine translation by jointly learning to align and translate"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2016.7472621"},{"key":"ref23","author":"chorowski","year":"2014","journal-title":"End-to-end continuous speech recognition using attention-based recurrent nn First results"},{"key":"ref26","first-page":"2048","article-title":"Show, attend and tell: Neural image caption generation with visual attention","author":"xu","year":"2015","journal-title":"Proceedings of the 32nd International Conference on Machine Learning ICML 2015"},{"key":"ref25","author":"wang","year":"2017","journal-title":"Tacotron A fully end-to-end text-to-speech synthesis model"}],"event":{"name":"2017 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","location":"Okinawa, Japan","start":{"date-parts":[[2017,12,16]]},"end":{"date-parts":[[2017,12,20]]}},"container-title":["2017 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/8260578\/8268903\/08268950.pdf?arnumber=8268950","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,8,13]],"date-time":"2022-08-13T06:17:28Z","timestamp":1660371448000},"score":1,"resource":{"primary":{"URL":"http:\/\/ieeexplore.ieee.org\/document\/8268950\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2017,12]]},"references-count":36,"URL":"https:\/\/doi.org\/10.1109\/asru.2017.8268950","relation":{},"subject":[],"published":{"date-parts":[[2017,12]]}}}