{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,9,8]],"date-time":"2024-09-08T08:13:21Z","timestamp":1725783201122},"reference-count":23,"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.2019.8683480","type":"proceedings-article","created":{"date-parts":[[2019,4,17]],"date-time":"2019-04-17T20:01:56Z","timestamp":1555531316000},"page":"6281-6285","source":"Crossref","is-referenced-by-count":14,"title":["End-to-end Feedback Loss in Speech Chain Framework via Straight-through Estimator"],"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":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2016.7472621"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D15-1166"},{"key":"ref12","article-title":"Tacotron: A fully end-to-end text-to-speech synthesis model","author":"wang","year":"2017","journal-title":"arXiv preprint arXiv 1703 10593"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/TASSP.1984.1164317"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.3115\/1075527.1075614"},{"key":"ref15","first-page":"cfp11srw-usb","article-title":"The Kaldi speech recognition toolkit","author":"povey","year":"0","journal-title":"2011 IEEE Workshop on Automatic Speech Recognition & Understanding"},{"key":"ref16","article-title":"First-pass large vocabulary continuous speech recognition using bi-directional recurrent DNNs","author":"hannun","year":"2014","journal-title":"arXiv preprint arXiv 1408 2873"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-24797-2_2"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2016.7472618"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/SLT.2018.8639528"},{"key":"ref4","article-title":"Estimating or propagating gradients through stochastic neurons for conditional computation","author":"bengio","year":"2013","journal-title":"arXiv preprint arXiv 1308 3432"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1558"},{"key":"ref6","article-title":"Distilling the knowledge in a neural network","author":"hinton","year":"2015","journal-title":"arXiv preprint arXiv 1503"},{"journal-title":"Neural networks for machine learning Coursera video lectures","year":"2012","author":"hinton","key":"ref5"},{"key":"ref8","article-title":"The concrete distribution: A continuous relaxation of discrete random variables","author":"maddison","year":"2016","journal-title":"arXiv preprint arXiv 1611 00712"},{"journal-title":"Categorical reparameterization with gumbel-softmax","year":"2017","author":"jang","key":"ref7"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU.2017.8268950"},{"journal-title":"The Speech Chain","year":"1993","author":"denes","key":"ref1"},{"key":"ref9","article-title":"Neural machine translation by jointly learning to align and translate","author":"bahdanau","year":"2014","journal-title":"arXiv preprint arXiv 1409 0473"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7953075"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P16-1009"},{"key":"ref21","first-page":"309","article-title":"Attention-based wav2text with feature transfer learning","author":"tjandra","year":"2017","journal-title":"2017 IEEE Automatic Speech Recognition and Understanding Workshop ASRU 2017 Okinawa Japan December 16-20 2017"},{"key":"ref23","first-page":"820","article-title":"Dual learning for machine translation","author":"he","year":"2016","journal-title":"Advances in neural information processing systems"}],"event":{"name":"ICASSP 2019 - 2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","start":{"date-parts":[[2019,5,12]]},"location":"Brighton, United Kingdom","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\/08683480.pdf?arnumber=8683480","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,7,15]],"date-time":"2022-07-15T03:21:35Z","timestamp":1657855295000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/8683480\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019,5]]},"references-count":23,"URL":"https:\/\/doi.org\/10.1109\/icassp.2019.8683480","relation":{},"subject":[],"published":{"date-parts":[[2019,5]]}}}