{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,10,29]],"date-time":"2024-10-29T19:32:05Z","timestamp":1730230325526,"version":"3.28.0"},"reference-count":14,"publisher":"IEEE","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2018,4]]},"DOI":"10.1109\/icassp.2018.8462375","type":"proceedings-article","created":{"date-parts":[[2018,9,21]],"date-time":"2018-09-21T22:24:48Z","timestamp":1537568688000},"page":"5229-5233","source":"Crossref","is-referenced-by-count":11,"title":["Says Who? Deep Learning Models for Joint Speech Recognition, Segmentation and Diarization"],"prefix":"10.1109","author":[{"given":"Amitrajit","family":"Sarkar","sequence":"first","affiliation":[]},{"given":"Surajit","family":"Dasgupta","sequence":"additional","affiliation":[]},{"given":"Sudip Kumar","family":"Naskar","sequence":"additional","affiliation":[]},{"given":"Sivaji","family":"Bandyopadhyay","sequence":"additional","affiliation":[]}],"member":"263","reference":[{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178838"},{"key":"ref11","article-title":"Improving speaker diarization","author":"barras","year":"0","journal-title":"PROC FALL 2004 RICH TRAN-SCRIPTION WORKSHOP (RT-04 2004"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1016\/j.sigpro.2007.11.017"},{"key":"ref13","first-page":"249","article-title":"Understanding the difficulty of training deep feedforward neural networks","author":"glorot","year":"2010","journal-title":"Proceedings of the Thirteenth International Conference on Artificial Intelligence and Statistics AISTATS 2010"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2011.2125954"},{"key":"ref4","article-title":"Librispeech: an ASR corpus based on public domain audio books","author":"panayotov","year":"2015","journal-title":"Proceedings of the International Conference on Acoustics Speech and Signal Processing (ICASSP)"},{"key":"ref3","article-title":"Deep speech 2: End-to-end speech recognition in english and mandarin","volume":"abs 1512 2595","author":"amodei","year":"2015","journal-title":"CoRR"},{"key":"ref6","article-title":"Learning phrase representations using RNN encoder-decoder for statistical machine translation","author":"cho","year":"2014","journal-title":"CoRR vol abs\/1406 1078"},{"key":"ref5","first-page":"1764","article-title":"Towards end-to-end speech recognition with recurrent neural networks","author":"graves","year":"2014","journal-title":"Proceedings of the 31th International Conference on Machine Learning ICML 2014"},{"key":"ref8","first-page":"369","article-title":"Connectionist temporal classification: labelling unsegmented sequence data with recurrent neural networks","author":"alex","year":"2006","journal-title":"Proceedings of the Twenty-Third International Conference on Machine Learning (ICML)"},{"key":"ref7","article-title":"Listen, attend and spell","author":"william","year":"2015","journal-title":"CoRR vol abs\/1508 01211"},{"key":"ref2","article-title":"Robust speaker diarization for meetings: ICSI rt06s evaluation system","author":"xavier","year":"2006","journal-title":"INTER-SPEECH 2006 - ICSLp Ninth International Conference on Spoken Language Processing"},{"key":"ref1","first-page":"4428","article-title":"Fast speaker diarization based on binary keys","author":"xavier","year":"2011","journal-title":"Proceedings of the IEEE International Conference on Acoustics Speech and Signal Processing ICASSP May 22–27 2011"},{"key":"ref9","article-title":"Deep speech: Scaling up end-to-end speech recognition","author":"hannun","year":"2014","journal-title":"CoRR vol abs\/1412 5567"}],"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\/08462375.pdf?arnumber=8462375","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2020,8,24]],"date-time":"2020-08-24T01:18:13Z","timestamp":1598231893000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/8462375\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2018,4]]},"references-count":14,"URL":"https:\/\/doi.org\/10.1109\/icassp.2018.8462375","relation":{},"subject":[],"published":{"date-parts":[[2018,4]]}}}