{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,9,8]],"date-time":"2024-09-08T12:56:15Z","timestamp":1725800175921},"reference-count":33,"publisher":"IEEE","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2018,4]]},"DOI":"10.1109\/icassp.2018.8461737","type":"proceedings-article","created":{"date-parts":[[2018,9,21]],"date-time":"2018-09-21T18:24:48Z","timestamp":1537554288000},"page":"706-710","source":"Crossref","is-referenced-by-count":10,"title":["End-to-End Sound Source Enhancement Using Deep Neural Network in the Modified Discrete Cosine Transform Domain"],"prefix":"10.1109","author":[{"given":"Yuma","family":"Koizumi","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Noboru","family":"Harada","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yoichi","family":"Haneda","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yusuke","family":"Hioka","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Kazunori","family":"Kobayashi","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref33","article-title":"Adam: A method for stochastic optimization","author":"kingma","year":"2015","journal-title":"Proc ICLR"},{"key":"ref32","article-title":"The third ‘CHiME’ speech separation and recognition challenge: dataset, task and baseline","author":"barker","year":"2015","journal-title":"Proc ASRU"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1016\/0167-6393(90)90011-W"},{"key":"ref30","doi-asserted-by":"crossref","DOI":"10.21437\/Interspeech.2017-1428","article-title":"SEGAN: Speech enhancement generative adversarial network","author":"pascual","year":"2017","journal-title":"Proc INTERSPEECH"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2013.2248715"},{"key":"ref11","article-title":"Non-negative matrix factorization for polyphonic music transcription","author":"smaragdis","year":"2003","journal-title":"Proc WASPAA"},{"key":"ref12","article-title":"Discriminatively trained recurrent neural networks for single-channel speech separation","author":"weninger","year":"2014","journal-title":"Proc GlobalSIP"},{"key":"ref13","article-title":"A deep neural network for time-domain signal reconstruction","author":"wang","year":"2015","journal-title":"Proc ICASSP"},{"key":"ref14","article-title":"Phase-sensitive and recognition-boosted speech separation using deep recurrent neural networks","author":"erdogan","year":"2015","journal-title":"Proc ICASSP"},{"key":"ref15","doi-asserted-by":"crossref","first-page":"7","DOI":"10.1109\/TASLP.2014.2364452","article-title":"A regression approach to speech enhancement based on deep neural networks","author":"xu","year":"2015","journal-title":"IEEE\/ACM Trans Audio Speech and Language Processing"},{"key":"ref16","article-title":"Pinpoint extraction of distant sound source based on DNN mapping from multiple beamforming outputs to prior SNR","author":"niwa","year":"2016","journal-title":"Proc ICASSP"},{"key":"ref17","article-title":"Deep clustering: Discriminative embeddings for segmentation and separation","author":"hershy","year":"2016","journal-title":"Proc ICASSP"},{"key":"ref18","article-title":"A perceptually-weighted deep neural network for monaural speech enhancement in various background noise conditions","author":"liu","year":"2017","journal-title":"Proc EU-SIP CO"},{"key":"ref19","article-title":"DNN-based source enhancement self-optimized by reinforcement learning using sound quality measurements","author":"koizumi","year":"2017","journal-title":"Proc ICASSP"},{"key":"ref28","article-title":"On relationships between amplitude and phase of short-time Fourier transform","author":"shimauchi","year":"2017","journal-title":"Proc ICASSP"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TCE.2008.4470033"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2011.2114881"},{"key":"ref3","article-title":"Multichannel end-to-end speech recognition","author":"ochiai","year":"2017","journal-title":"Proc ICML"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1177\/1084713808326455"},{"key":"ref29","article-title":"Improving the perceptual quality of ideal binary masked speech","author":"lightburn","year":"2017","journal-title":"Proc ICASSP"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1016\/S0167-6393(02)00095-X"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2017.2662232"},{"key":"ref7","article-title":"Intelligent hearing aids: The next revolution","author":"zhang","year":"2016","journal-title":"Proc EMBC"},{"key":"ref2","article-title":"The NTT CHiME-3 system: Advances in speech enhancement and recognition for mobile multi-microphone devices","author":"yoshioka","year":"2015","journal-title":"Proc ASRU"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TASSP.1984.1164453"},{"journal-title":"Speech Enhancement","year":"2005","author":"benesty","key":"ref1"},{"key":"ref20","first-page":"465","article-title":"The importance of phase in speech enhancement","author":"paliwal","year":"2010","journal-title":"Speech Communication"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2017.2696307"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2015.2512042"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/TASSP.1986.1164954"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2016-1459"},{"key":"ref26","article-title":"Aliasing reduction for modified discrete cosine transform domain filtering and its application to speech enhancement","author":"keuch","year":"2007","journal-title":"Proc WASPAA"},{"key":"ref25","first-page":"52","article-title":"Modified discrete cosine transform-Its implications for audio coding and error concealment","author":"wang","year":"2003","journal-title":"J Audio Eng Soc"}],"event":{"name":"ICASSP 2018 - 2018 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","start":{"date-parts":[[2018,4,15]]},"location":"Calgary, AB","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\/08461737.pdf?arnumber=8461737","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2020,8,23]],"date-time":"2020-08-23T22:28:16Z","timestamp":1598221696000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/8461737\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2018,4]]},"references-count":33,"URL":"https:\/\/doi.org\/10.1109\/icassp.2018.8461737","relation":{},"subject":[],"published":{"date-parts":[[2018,4]]}}}