{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,17]],"date-time":"2026-09-17T04:15:39Z","timestamp":1789618539846,"version":"build-2803163510"},"reference-count":39,"publisher":"IEEE","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2018,4]]},"DOI":"10.1109\/icassp.2018.8461282","type":"proceedings-article","created":{"date-parts":[[2018,9,21]],"date-time":"2018-09-21T22:24:48Z","timestamp":1537568688000},"page":"2256-2260","source":"Crossref","is-referenced-by-count":9,"title":["On Using Backpropagation for Speech Texture Generation and Voice Conversion"],"prefix":"10.1109","author":[{"given":"Jan","family":"Chorowski","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ron J.","family":"Weiss","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Rif A.","family":"Saurous","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Samy","family":"Bengio","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref39","doi-asserted-by":"crossref","DOI":"10.21437\/Interspeech.2017-1452","article-title":"Tacotron: A fully end-to-end text-to-speech synthesis model","author":"wang","year":"2017","journal-title":"Proc INTERSPEECH"},{"key":"ref38","article-title":"A learned representation for artistic style","author":"dumoulin","year":"2017","journal-title":"Proc ICLR"},{"key":"ref33","author":"wyse","year":"2017","journal-title":"Audio spectrogram representations for processing with convolutional neural networks"},{"key":"ref32","author":"ulyanov","year":"2016","journal-title":"Audio texture synthesis and style transfer"},{"key":"ref31","article-title":"Audio deep-dream: Optimizing raw audio with convolutional networks","author":"roberts","year":"2016","journal-title":"Proc ISMIR"},{"key":"ref30","article-title":"A powerful generative model using random weights for the deep image representation","author":"he","year":"2016","journal-title":"Advances in neural information processing systems"},{"key":"ref37","first-page":"694","article-title":"Perceptual losses for real-time style transfer and super-resolution","author":"johnson","year":"2016","journal-title":"European Conference on Comnpter Vision"},{"key":"ref36","first-page":"1349","article-title":"Texture networks: Feed-forward synthesis of textures and stylized images","author":"ulyanov","year":"2016","journal-title":"Proc ICML"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2016-1066"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1016\/S0167-6393(98)00085-5"},{"key":"ref10","first-page":"184","article-title":"Learning a deep convolutional network for image super-resolution","author":"dong","year":"2014","journal-title":"European Conference on Computer Vision"},{"key":"ref11","author":"simonyan","year":"2013","journal-title":"Deep Inside Convolutional Networks Visualising Image Classification Models and Saliency Maps"},{"key":"ref12","author":"goodfellow","year":"2014","journal-title":"Explaining and Harnessing Adversarial Examples"},{"key":"ref13","first-page":"262","article-title":"Texture synthesis using convolutional neural networks","author":"gatys","year":"2015","journal-title":"Advances in neural information processing systems"},{"key":"ref14","author":"gatys","year":"2015","journal-title":"A neural algorithm of artistic style"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/TIT.1962.1057698"},{"key":"ref16","doi-asserted-by":"crossref","DOI":"10.1109\/ASPAA.2009.5346467","article-title":"Sound texture synthesis via filter statistics","author":"mcdermott","year":"2009","journal-title":"IEEE Workshop on Applications of Signal Processing to Audio and Acoustics"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1016\/j.neuron.2011.06.032"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1023\/A:1026553619983"},{"key":"ref19","author":"zhang","year":"2017","journal-title":"Towards End-to-End Speech Recognition with Deep Convolutional Neural Networks"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7953194"},{"key":"ref4","author":"bahdanau","year":"2014","journal-title":"Neural machine translation by jointly learning to align and translate"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7952132"},{"key":"ref3","article-title":"Attention-based models for speech recognition","author":"chorowski","year":"2015","journal-title":"Advances in neural information processing systems"},{"key":"ref6","author":"wu","year":"2016","journal-title":"Google's neural machine translation system Bridging the gap between human and machine translation"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.4135\/9781412985130"},{"key":"ref5","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":"ref8","author":"v d oord","year":"2016","journal-title":"WaveNet A Generative Model for Raw Audio"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2016-522"},{"key":"ref2","first-page":"1764","article-title":"Towards end-to-end speech recognition with recurrent neural networks","author":"graves","year":"2014","journal-title":"Proc ICML"},{"key":"ref9","author":"radford","year":"2015","journal-title":"Unsupervised Representation learning with deep convolutional generative adversarial networks CoRR"},{"key":"ref1","article-title":"Imagenet classification with deep convolutional neural networks","author":"krizhevsky","year":"2012","journal-title":"Advances in neural information processing systems"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1145\/1143844.1143891"},{"key":"ref22","article-title":"The kaldi speech recognition toolkit","author":"povey","year":"2011","journal-title":"Proc ASRU"},{"key":"ref21","author":"kingma","year":"2014","journal-title":"Adam A method for stochastic optimization"},{"key":"ref24","author":"abadi","year":"2016","journal-title":"Tensorfiow Large-scale machine learning on heterogeneous distributed systems"},{"key":"ref23","article-title":"Learning the speech front-end with raw waveform CLDNNs","author":"sainath","year":"2015","journal-title":"Proc Lnterspeech"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1145\/279232.279236"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/TASSP.1984.1164317"}],"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\/08461282.pdf?arnumber=8461282","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2020,8,24]],"date-time":"2020-08-24T05:00:25Z","timestamp":1598245225000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/8461282\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2018,4]]},"references-count":39,"URL":"https:\/\/doi.org\/10.1109\/icassp.2018.8461282","relation":{},"subject":[],"published":{"date-parts":[[2018,4]]}}}