{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,10,30]],"date-time":"2024-10-30T07:24:33Z","timestamp":1730273073237,"version":"3.28.0"},"reference-count":38,"publisher":"IEEE","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2018,11]]},"DOI":"10.1109\/iscslp.2018.8706689","type":"proceedings-article","created":{"date-parts":[[2019,5,20]],"date-time":"2019-05-20T22:58:35Z","timestamp":1558393115000},"page":"76-80","source":"Crossref","is-referenced-by-count":4,"title":["A Progressive Deep Learning Approach to Child Speech Separation"],"prefix":"10.1109","author":[{"given":"Xin","family":"Wang","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jun","family":"Du","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Lei","family":"Sun","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Qing","family":"Wang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Chin-Hui","family":"Lee","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2011.2114881"},{"key":"ref33","doi-asserted-by":"crossref","DOI":"10.1049\/cp:19991218","article-title":"Learning to forget: Continual prediction with LSTM","author":"gers","year":"1999"},{"key":"ref32","first-page":"1310","article-title":"On the difficulty of training recurrent neural networks","author":"pascanu","year":"2013","journal-title":"International Conference on Machine Learning"},{"article-title":"Theory and applications of multidimensional\nscaling","year":"1994","author":"young","key":"ref31"},{"key":"ref30","first-page":"1535","article-title":"A gender mixture detection approach to unsupervised single-channel speech separation based on deep neural networks","author":"yannan","year":"2017","journal-title":"Audio Speech and Language Processing IEEE\/ACM Transactions on"},{"key":"ref37","first-page":"862","article-title":"Perceptual evaluation of speech quality (PESQ): An objective method for end-toend speech quality assessment of narrow-band telephone networks and speech codecs","author":"rix","year":"2001","journal-title":"ITU-T Recommendation"},{"key":"ref36","article-title":"An introduction to computational networks and the computational network toolkit","author":"yu","year":"2014","journal-title":"Microsoft Technical Report MSR-TR-2014-112"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/TASSP.1982.1163920"},{"key":"ref34","article-title":"Densely connected convolutional networks","author":"huang","year":"2016","journal-title":"arXiv preprint arXiv 1608 06993"},{"key":"ref10","first-page":"2614","article-title":"Single-channel speech separation using sparse non-negative matrix factorization, in","author":"schmidt","year":"2006","journal-title":"Proc INTERSPEECH"},{"key":"ref11","first-page":"66","article-title":"Deep NMF for speech separation, in","author":"roux","year":"2015","journal-title":"Proc IEEE Int Conf Acoust Speech Signal Process"},{"journal-title":"Computational Auditory Scene Analysis Principles Algorithms and Applications","year":"2006","author":"wang","key":"ref12"},{"key":"ref13","doi-asserted-by":"crossref","first-page":"122","DOI":"10.1109\/TASL.2012.2215591","article-title":"An unsupervised approach to cochannel speech separation","volume":"21","author":"hu","year":"2013","journal-title":"IEEE Trans Audio Speech and Language Processing"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1162\/neco.2006.18.7.1527"},{"key":"ref15","doi-asserted-by":"crossref","first-page":"504","DOI":"10.1126\/science.1127647","article-title":"Reducing the dimensionality of data with neural networks","volume":"313","author":"hinton","year":"2006","journal-title":"Science"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/LSP.2013.2291240"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2014.2364452"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2014.6854479"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2016.2623559"},{"key":"ref28","article-title":"CSR-I (WSJ0) complete","author":"garofalo","year":"0","journal-title":"Linguistic Data Consortium"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1121\/1.426686"},{"key":"ref27","article-title":"Unsupervised single-channel speech separation via deep neural network for different gender mixtures","author":"yannan","year":"2016","journal-title":"Signal and Information Processing Association Annual Summit and Conference (APSIPA)"},{"article-title":"Bergelson Seedlings HomeBank Corpus","year":"0","author":"bergelson","key":"ref3"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2010.2064307"},{"year":"0","key":"ref29"},{"journal-title":"Mixture Models Inference and Applications to Clustering","year":"1988","author":"mclachlan","key":"ref5"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2016-1118"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/FSKD.2007.488"},{"key":"ref2","first-page":"37","article-title":"Investigating recognition of children’s speech","author":"giuliani","year":"2003","journal-title":"Proc ICASSP"},{"key":"ref9","first-page":"1009","article-title":"Factorial models and refiltering for speech separation and denoising","author":"roweis","year":"2003","journal-title":"Proc EUROSPEECH"},{"key":"ref1","article-title":"Separation of added speech signals by digital comb filtering","author":"shields","year":"1970","journal-title":"S M thesis"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/GlobalSIP.2014.7032183"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2014.2352935"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2013.6639038"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/HSCMA.2017.7895577"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2016-224"},{"key":"ref26","article-title":"Speech separation based on improved deep neural networks with dual outputs of speech features for both target and interfering speakers","author":"yanhui","year":"2014","journal-title":"Chinese Spoken Language Processing (ISCSLP) 2014 9th International Symposium on IEEE"},{"key":"ref25","article-title":"Multi-objective learning and mask-based postprocessing for deep neural network based speech enhancement","author":"yong","year":"2017","journal-title":"arXiv preprint arXiv 1703 06870"}],"event":{"name":"2018 11th International Symposium on Chinese Spoken Language Processing (ISCSLP)","start":{"date-parts":[[2018,11,26]]},"location":"Taipei City, Taiwan","end":{"date-parts":[[2018,11,29]]}},"container-title":["2018 11th International Symposium on Chinese Spoken Language Processing (ISCSLP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/8701133\/8706262\/08706689.pdf?arnumber=8706689","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2020,8,24]],"date-time":"2020-08-24T06:15:22Z","timestamp":1598249722000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/8706689\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2018,11]]},"references-count":38,"URL":"https:\/\/doi.org\/10.1109\/iscslp.2018.8706689","relation":{},"subject":[],"published":{"date-parts":[[2018,11]]}}}