{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,14]],"date-time":"2025-10-14T11:31:50Z","timestamp":1760441510109,"version":"3.28.0"},"reference-count":30,"publisher":"IEEE","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2018,4]]},"DOI":"10.1109\/icassp.2018.8462311","type":"proceedings-article","created":{"date-parts":[[2018,9,21]],"date-time":"2018-09-21T22:24:48Z","timestamp":1537568688000},"page":"5234-5238","source":"Crossref","is-referenced-by-count":19,"title":["A Novel LSTM-Based Speech Preprocessor for Speaker Diarization in Realistic Mismatch Conditions"],"prefix":"10.1109","author":[{"given":"Lei","family":"Sun","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jun","family":"Du","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Tian","family":"Gao","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yu-Ding","family":"Lu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yu","family":"Tsao","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Chin-Hui","family":"Lee","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Neville","family":"Ryant","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.1996.543199"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-540-49127-9_44"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2013.6639038"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2014.2305833"},{"key":"ref13","first-page":"436","article-title":"Speech enhancement based on deep denoising autoencoder","author":"lu","year":"0","journal-title":"Interspeech 2013"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2013.2250961"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/LSP.2013.2291240"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2016-224"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/HSCMA.2017.7895577"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7953197"},{"key":"ref19","article-title":"Diartk: An open source toolkit for research in multistream speaker diarization and its application to meetings recordings","author":"vijayasenan","year":"2012","journal-title":"Thirteenth Annual Conference of the International Speech Communication Association"},{"journal-title":"Bergelson Seedlings HomeBank Corpus","year":"0","author":"bergelson","key":"ref28"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2014.6853565"},{"key":"ref27","first-page":"74","article-title":"Exploring Autism Spectrum Disorders using HLT","author":"parish-morris","year":"2016","journal-title":"CLPsych"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2011.2125954"},{"key":"ref6","article-title":"In-tegrating online i-vector extractor with information bottleneck based speaker diarization system","author":"madikeri","year":"2015","journal-title":"Tech Rep IDIAP"},{"journal-title":"Beamformit the fast and robust acoustic beamformer","year":"2006","author":"anguera","key":"ref29"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2014.2346315"},{"key":"ref8","doi-asserted-by":"crossref","first-page":"i","DOI":"10.1109\/ICASSP.2004.1326000","article-title":"The elisa consortium approaches in broadcast news speaker segmentation during the nist 2003 rich transcription evaluation","volume":"1","author":"moraru","year":"2004","journal-title":"Acoustics Speech and Signal Processing 2004 Proceedings (ICASSP ‘04) IEEE International Conference"},{"key":"ref7","first-page":"i","article-title":"Two-way cluster voting to improve speaker di-arisation performance","volume":"1","author":"tranter","year":"2005","journal-title":"Acoustics Speech and Signal Processing 2005 Proceedings (ICASSP ‘05) IEEE International Conference"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2009.2015698"},{"key":"ref9","doi-asserted-by":"crossref","first-page":"1109","DOI":"10.1109\/TASSP.1984.1164453","article-title":"Speech enhancement using a minimum-mean square error short-time spectral amplitude estimator","volume":"32","author":"ephraim","year":"1984","journal-title":"IEEE Transactions on Acoustics Speech and Signal Processing"},{"key":"ref1","doi-asserted-by":"crossref","first-page":"509","DOI":"10.1007\/978-3-540-68585-2_47","article-title":"The icsi rt07s speaker diarization system","author":"wooters","year":"2008","journal-title":"Multimodal Technologies for Perception of Humans"},{"key":"ref20","first-page":"175","article-title":"The htk book","volume":"3","author":"young","year":"2002","journal-title":"Cambridge University Engineering Department"},{"key":"ref22","first-page":"1310","article-title":"On the difficulty of training recurrent neural networks","author":"pascanu","year":"2013","journal-title":"International Conference on Machine Learning"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2013.6639170"},{"journal-title":"Densely Connected Convolutional Networks","year":"2016","author":"huang","key":"ref24"},{"journal-title":"Learning to forget Continual prediction with lstm","year":"1999","author":"gers","key":"ref23"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1007\/s10579-007-9040-x"},{"key":"ref25","article-title":"Densely connected progressive learning for lstm-based speech enhancement","author":"tian","year":"2018","journal-title":"Submitted to ICASSP"}],"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\/08462311.pdf?arnumber=8462311","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2020,8,24]],"date-time":"2020-08-24T05:03:07Z","timestamp":1598245387000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/8462311\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2018,4]]},"references-count":30,"URL":"https:\/\/doi.org\/10.1109\/icassp.2018.8462311","relation":{},"subject":[],"published":{"date-parts":[[2018,4]]}}}