{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,11,19]],"date-time":"2025-11-19T07:00:20Z","timestamp":1763535620785,"version":"build-2065373602"},"reference-count":27,"publisher":"IEEE","license":[{"start":{"date-parts":[[2019,5,1]],"date-time":"2019-05-01T00:00:00Z","timestamp":1556668800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2019,5,1]],"date-time":"2019-05-01T00:00:00Z","timestamp":1556668800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2019,5]]},"DOI":"10.1109\/icassp.2019.8683443","type":"proceedings-article","created":{"date-parts":[[2019,4,17]],"date-time":"2019-04-17T16:01:56Z","timestamp":1555516916000},"page":"6021-6025","source":"Crossref","is-referenced-by-count":22,"title":["Knowledge Distillation for Small Foot-print Deep Speaker Embedding"],"prefix":"10.1109","author":[{"given":"Shuai","family":"Wang","sequence":"first","affiliation":[{"name":"MoE Key Lab of Artificial Intelligence SpeechLab, Shanghai Jiao Tong University, Shanghai, China"}]},{"given":"Yexin","family":"Yang","sequence":"additional","affiliation":[{"name":"MoE Key Lab of Artificial Intelligence SpeechLab, Shanghai Jiao Tong University, Shanghai, China"}]},{"given":"Tianzhe","family":"Wang","sequence":"additional","affiliation":[{"name":"MoE Key Lab of Artificial Intelligence SpeechLab, Shanghai Jiao Tong University, Shanghai, China"}]},{"given":"Yanmin","family":"Qian","sequence":"additional","affiliation":[{"name":"MoE Key Lab of Artificial Intelligence SpeechLab, Shanghai Jiao Tong University, Shanghai, China"}]},{"given":"Kai","family":"Yu","sequence":"additional","affiliation":[{"name":"MoE Key Lab of Artificial Intelligence SpeechLab, Shanghai Jiao Tong University, Shanghai, China"}]}],"member":"263","reference":[{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1545"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1769"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1929"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-92"},{"article-title":"Distilling the knowledge in a neural network","year":"2015","author":"hinton","key":"ref15"},{"article-title":"Deep model compression: Distilling knowledge from noisy teachers","year":"2016","author":"sau","key":"ref16"},{"key":"ref17","article-title":"Learning small-size dnn with output-distribution-based criteria","author":"li","year":"2014","journal-title":"Fifteenth Annual Conference of the International Speech Communication Association"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2016-1190"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1589"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2010.2064307"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/SLT.2018.8639622"},{"key":"ref3","article-title":"Joint factor analysis of speaker and session variability: Theory and algorithms","author":"kenny","year":"2005","journal-title":"CRIM Montreal (Report) CRIM-06\/08-13"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-1608"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ISCSLP.2018.8706632"},{"key":"ref8","doi-asserted-by":"crossref","first-page":"999","DOI":"10.21437\/Interspeech.2017-620","article-title":"Deep neural network embeddings for text-independent speaker verification","author":"snyder","year":"2017","journal-title":"Proc Interspeech 2017"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461375"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2006.1659966"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8462508"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1006\/dspr.1999.0361"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8462209"},{"key":"ref22","article-title":"Multi-task learning for text-dependent speaker verification","author":"chen","year":"2015","journal-title":"Sixteenth Annual Conference of the International Speech Communication Association"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2014.6854363"},{"article-title":"Generalized end-to-end loss for speaker verification","year":"2017","author":"wan","key":"ref24"},{"key":"ref23","first-page":"1151","article-title":"Investigation of bottleneck features and multilingual deep neural networks for speaker verification","author":"tian","year":"2015","journal-title":"InterSpeech"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-950"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7953072"}],"event":{"name":"ICASSP 2019 - 2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","start":{"date-parts":[[2019,5,12]]},"location":"Brighton, UK","end":{"date-parts":[[2019,5,17]]}},"container-title":["ICASSP 2019 - 2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/8671773\/8682151\/08683443.pdf?arnumber=8683443","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,21]],"date-time":"2025-08-21T18:18:59Z","timestamp":1755800339000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/8683443\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019,5]]},"references-count":27,"URL":"https:\/\/doi.org\/10.1109\/icassp.2019.8683443","relation":{},"subject":[],"published":{"date-parts":[[2019,5]]}}}