{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,15]],"date-time":"2026-06-15T23:15:30Z","timestamp":1781565330932,"version":"3.54.5"},"reference-count":38,"publisher":"IEEE","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2018,4]]},"DOI":"10.1109\/icassp.2018.8461829","type":"proceedings-article","created":{"date-parts":[[2018,9,21]],"date-time":"2018-09-21T22:24:48Z","timestamp":1537568688000},"page":"4784-4788","source":"Crossref","is-referenced-by-count":157,"title":["Efficiently Trainable Text-to-Speech System Based on Deep Convolutional Networks with Guided Attention"],"prefix":"10.1109","author":[{"given":"Hideyuki","family":"Tachibana","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Katsuya","family":"Uenoyama","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Shunsuke","family":"Aihara","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref38","first-page":"2416","article-title":"CrowdMOS: An approach for crowdsourcing mean opinion score studies","author":"ribeiro","year":"2011","journal-title":"Proc ICASSP"},{"key":"ref33","article-title":"Multi-scale context aggregation by dilated convolutions","author":"yu","year":"2016","journal-title":"Proc ICLR"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.629"},{"key":"ref31","first-page":"2377","article-title":"Training very deep networks","author":"srivastava","year":"2015","journal-title":"Proc NIPS"},{"key":"ref30","first-page":"255","article-title":"The handbook of brain theory and neural networks","author":"lecun","year":"1998","journal-title":"chapter Convolutional networks for images speech and time series"},{"key":"ref37","article-title":"Adam: A method for stochastic optimization","author":"kingma","year":"2014","journal-title":"Proc ICLR 2015"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.123"},{"key":"ref35","article-title":"Chainer: A next-generation open source framework for deep learning","author":"tokui","year":"2015","journal-title":"Proc Workshop LearningSys NIPS"},{"key":"ref34","author":"ito","year":"2017","journal-title":"The LJ speech dataset"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178816"},{"key":"ref11","first-page":"859","article-title":"An investigation of recurrent neural network architectures for statistical parametric speech synthesis","author":"achanta","year":"2015","journal-title":"Proc INTERSPEECH"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2016.7472657"},{"key":"ref13","author":"van den oord","year":"2016","journal-title":"WaveNet A Generative Model for Raw Audio"},{"key":"ref14","article-title":"Char2wav: End-to-end speech synthesis","author":"sotelo","year":"2017","journal-title":"Proc ICLR"},{"key":"ref15","first-page":"195","article-title":"Deep voice: Real-time neural text-to-speech","author":"arik","year":"2017","journal-title":"Proc ICML"},{"key":"ref16","article-title":"Deep voice 2: Multi-speaker neural text-to-speech","author":"arik","year":"2017","journal-title":"Proc NIPS"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/D14-1179"},{"key":"ref18","first-page":"3104","article-title":"Sequence to sequence learning with neural networks","author":"sutskever","year":"2014","journal-title":"Proc NIPS"},{"key":"ref19","article-title":"A neural conversational model","author":"vinyals","year":"2015","journal-title":"Proc ICML Deep Learn Workshop"},{"key":"ref28","author":"mowlee","year":"2016","journal-title":"Single Channel Phase-Aware Signal Processing in Speech Communication Theory and Practice"},{"key":"ref4","article-title":"A TensorFlow implementation of Tacotron: A fully end-to-end text-to-speech synthesis model","author":"park","year":"2017","journal-title":"Available at GitHub"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/TASSP.1984.1164317"},{"key":"ref3","author":"barron","year":"2017","journal-title":"Implementation of Google's Tacotron in Ten-sorFlow"},{"key":"ref6","article-title":"PyTorch implementation of Tacotron speech synthesis model","author":"yamamoto","year":"2017","journal-title":"Available at GitHub"},{"key":"ref29","article-title":"Real-time signal estimation from modified short-time fourier transform magnitude spectra","volume":"15","author":"zhu","year":"2007","journal-title":"IEEE Trans ASLP"},{"key":"ref5","article-title":"Tacotron speech synthesis implemented in Tensor-Flow, with samples and a pre-trained model","author":"ito","year":"2017","journal-title":"Available at GitHub"},{"key":"ref8","first-page":"7962","article-title":"Statistical parametric speech synthesis using deep neural networks","author":"zen","year":"2013","journal-title":"Proc ICASSP"},{"key":"ref7","first-page":"1243","article-title":"Convolutional sequence to sequence learning","author":"gehring","year":"2017","journal-title":"Proc ICML"},{"key":"ref2","doi-asserted-by":"crossref","DOI":"10.21437\/Interspeech.2017-1452","article-title":"Tacotron: Towards end-to-end speech synthesis","author":"wang","year":"2017","journal-title":"Proc INTERSPEECH"},{"key":"ref9","first-page":"1964","article-title":"TTS synthesis with bidirectional LSTM based recurrent neural networks","author":"fan","year":"2014","journal-title":"Proc INTERSPEECH"},{"key":"ref1","author":"goodfellow","year":"2016","journal-title":"Deep Learning"},{"key":"ref20","first-page":"3776","article-title":"Building end-to-end dialogue systems using generative hierarchical neural network models","author":"serban","year":"2016","journal-title":"Proc AAAI"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/D14-1181"},{"key":"ref21","article-title":"Neural machine translation by jointly learning to align and translate","author":"bahdanau","year":"2014","journal-title":"Proc ICLR 2015"},{"key":"ref24","author":"kalchbrenner","year":"2016","journal-title":"Neural Machine Translation in Linear Time"},{"key":"ref23","article-title":"Character-level convolutional networks for text classification","author":"zhang","year":"2015","journal-title":"Proc NIPS"},{"key":"ref26","article-title":"Quasi-recurrent neural networks","author":"bradbury","year":"2016","journal-title":"Proceedings of ICLR 2017"},{"key":"ref25","author":"dauphin","year":"2016","journal-title":"Language Modeling with Gated Convolutional Networks[J]"}],"event":{"name":"ICASSP 2018 - 2018 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","location":"Calgary, AB","start":{"date-parts":[[2018,4,15]]},"end":{"date-parts":[[2018,4,20]]}},"container-title":["2018 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/8450881\/8461260\/08461829.pdf?arnumber=8461829","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2020,8,23]],"date-time":"2020-08-23T22:32:34Z","timestamp":1598221954000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/8461829\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2018,4]]},"references-count":38,"URL":"https:\/\/doi.org\/10.1109\/icassp.2018.8461829","relation":{},"subject":[],"published":{"date-parts":[[2018,4]]}}}