{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,10,30]],"date-time":"2024-10-30T14:04:19Z","timestamp":1730297059388,"version":"3.28.0"},"reference-count":36,"publisher":"IEEE","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2018,12]]},"DOI":"10.1109\/slt.2018.8639630","type":"proceedings-article","created":{"date-parts":[[2019,2,14]],"date-time":"2019-02-14T18:36:34Z","timestamp":1550169394000},"page":"1029-1035","source":"Crossref","is-referenced-by-count":3,"title":["Investigating Deep Neural Networks for Speaker Diarization in the DIHARD Challenge"],"prefix":"10.1109","author":[{"given":"Ivan","family":"Himawan","sequence":"first","affiliation":[]},{"given":"Md Hafizur","family":"Rahman","sequence":"additional","affiliation":[]},{"given":"Sridha","family":"Sridharan","sequence":"additional","affiliation":[]},{"given":"Clinton","family":"Fookes","sequence":"additional","affiliation":[]},{"given":"Ahilan","family":"Kanagasundaram","sequence":"additional","affiliation":[]}],"member":"263","reference":[{"key":"ref33","first-page":"4654","article-title":"Improving out-domain PLDA speaker verification using unsupervised interdataset variability compensation approach","author":"kanagasundaram","year":"2015","journal-title":"Proceedings of IEEE International Conference on Acoustics Speech and Signal Processing"},{"key":"ref32","first-page":"260","article-title":"Unsupervised domain adaptation for i-vector speaker recognition","author":"garcia-romero","year":"2014","journal-title":"Proc Odyssey"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2016-1380"},{"key":"ref30","first-page":"448","article-title":"Batch normalization: Accelerating deep network training by reducing internal covariate shift","author":"ioffe","year":"2015","journal-title":"Proceedings of International Conference on Machine Learning"},{"key":"ref36","article-title":"The kaldi speech recognition toolkit","author":"povey","year":"2011","journal-title":"Proceedings of IEEE Workshop on Automatic Speech Recognition and Understanding"},{"key":"ref35","doi-asserted-by":"crossref","first-page":"1581","DOI":"10.21437\/Interspeech.2017-668","article-title":"Domain mismatch modeling of out-domain ivectors for PLDA speaker verification","author":"rahman","year":"2017","journal-title":"Proceedings of Interspeech"},{"key":"ref34","first-page":"1017","article-title":"Dataset-invariant covariance normalization for out-domain PLDA speaker verification","author":"rahman","year":"2015","journal-title":"Proceedings of Interspeech"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/MLSP.2016.7738816"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461375"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/EUSIPCO.2015.7362751"},{"key":"ref13","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":"Proceedings of Interspeech"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2014.6854363"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2016.7472652"},{"article-title":"Deep speaker: an end-to-end neural speaker embedding system","year":"2017","author":"li","key":"ref16"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298682"},{"key":"ref18","first-page":"107","article-title":"Speaker diarization using deep recurrent convolutional neural networks for speaker embeddings","author":"cyrta","year":"2017","journal-title":"Proceedings of 38th International Conference on Information Systems Architecture and Technology"},{"key":"ref19","first-page":"1","article-title":"Learning embeddings for speaker clustering based on voice equality","author":"lukic","year":"2017","journal-title":"Proceedings of IEEE International Workshop on Machine Learning for Signal Processing"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.21236\/ADA613971"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2006.878261"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/MSP.2012.2205597"},{"key":"ref3","article-title":"Automatic segmentation, classification and clustering of broadcast news audio","volume":"1997","author":"siegler","year":"1997","journal-title":"Proc DARPA Speech Recognition Workshop"},{"key":"ref6","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":"ref29","first-page":"3096","article-title":"Speaker diarization with i-vectors from DNN senone posteriors","author":"sell","year":"2015","journal-title":"Proceedings of Interspeech"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2010.2081790"},{"article-title":"Bergelson seedlings homebank corpus","year":"2016","author":"bergelson","key":"ref8"},{"article-title":"First DIHARD challenge evaluation plan","year":"2018","author":"ryant","key":"ref7"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7953094"},{"article-title":"DIHARD corpus","year":"2018","author":"ryant","key":"ref9"},{"key":"ref1","doi-asserted-by":"crossref","first-page":"356","DOI":"10.1109\/TASL.2011.2125954","article-title":"Speaker diarization: A review of recent research","volume":"2","author":"mir\u00f3","year":"2012","journal-title":"IEEE Transactions on Audio Speech and Language Processing"},{"key":"ref20","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":"synder","year":"2017","journal-title":"Proceedings of Interspeech"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.21437\/Odyssey.2016-59"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/SLT.2014.7078610"},{"key":"ref24","doi-asserted-by":"crossref","DOI":"10.21437\/Interspeech.2010-774","article-title":"The QUT-NOISE-TIMIT corpus for the evaluation of voice activity detection algorithms","author":"dean","year":"2010","journal-title":"Proceedings of Interspeech"},{"year":"0","key":"ref23","article-title":"Havic pilot transcription"},{"key":"ref26","article-title":"Joint factor analysis of speaker and session variability: Theory and algorithms","author":"kenny","year":"2005","journal-title":"CRIM-06\/08-13 Tech Rep"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2010.2064307"}],"event":{"name":"2018 IEEE Spoken Language Technology Workshop (SLT)","start":{"date-parts":[[2018,12,18]]},"location":"Athens, Greece","end":{"date-parts":[[2018,12,21]]}},"container-title":["2018 IEEE Spoken Language Technology Workshop (SLT)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/8632666\/8639030\/08639630.pdf?arnumber=8639630","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,1,27]],"date-time":"2022-01-27T00:33:02Z","timestamp":1643243582000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/8639630\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2018,12]]},"references-count":36,"URL":"https:\/\/doi.org\/10.1109\/slt.2018.8639630","relation":{},"subject":[],"published":{"date-parts":[[2018,12]]}}}