{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,2]],"date-time":"2026-05-02T15:01:51Z","timestamp":1777734111949,"version":"3.51.4"},"reference-count":31,"publisher":"IEEE","license":[{"start":{"date-parts":[[2022,5,23]],"date-time":"2022-05-23T00:00:00Z","timestamp":1653264000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2022,5,23]],"date-time":"2022-05-23T00:00:00Z","timestamp":1653264000000},"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":[[2022,5,23]]},"DOI":"10.1109\/icassp43922.2022.9746806","type":"proceedings-article","created":{"date-parts":[[2022,4,27]],"date-time":"2022-04-27T15:50:34Z","timestamp":1651074634000},"page":"8102-8106","source":"Crossref","is-referenced-by-count":96,"title":["TitaNet: Neural Model for Speaker Representation with 1D Depth-Wise Separable Convolutions and Global Context"],"prefix":"10.1109","author":[{"given":"Nithin Rao","family":"Koluguri","sequence":"first","affiliation":[{"name":"NVIDIA,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Taejin","family":"Park","sequence":"additional","affiliation":[{"name":"NVIDIA,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Boris","family":"Ginsburg","sequence":"additional","affiliation":[{"name":"NVIDIA,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref31","article-title":"Nemo: a toolkit for building ai applications using neural modules","author":"kuchaiev","year":"2019"},{"key":"ref30","article-title":"BUT system description to voxceleb speaker recognition challenge 2019","author":"zeinali","year":"2019"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-2059"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-2650"},{"key":"ref12","article-title":"Bayesian speaker verification with heavy-tailed priors","author":"kenny","year":"2010","journal-title":"Odyssey"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1893"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1016\/j.csl.2021.101254"},{"key":"ref15","article-title":"The AMI meeting corpus: A preannouncement","author":"carletta","year":"2005","journal-title":"Int Workshop Mach Learn Multimodal Interact"},{"key":"ref16","article-title":"The NIST speaker recognition evaluations: 1996-2001","author":"martin","year":"2001","journal-title":"Odyssey"},{"key":"ref17","article-title":"CallHome american english speech","author":"canavan","year":"1997","journal-title":"Linguistic Data Consortium"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053889"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00482"},{"key":"ref28","first-page":"38","article-title":"Auto-tuning spectral clustering for speaker diarization using normalized maximum eigengap","volume":"27","author":"park","year":"2019","journal-title":"IEEE Signal Processing Letters"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1515"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-3015"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8683649"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8462575"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3061885"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-1446"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053198"},{"key":"ref7","article-title":"State-of-the-art speaker recognition for telephone and video speech: The JHU-MIT submission forNISTSRE18","author":"villalba","year":"2019","journal-title":"InterSpeech"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461375"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-941"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2014.6854363"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1929"},{"key":"ref22","article-title":"Fisher english training speech part 1 transcripts","author":"cieri","year":"2004","journal-title":"Linguistic Data Consortium"},{"key":"ref21","article-title":"Switchboard-1 release 2 LDC97S62","author":"godfrey","year":"1993","journal-title":"Linguistic Data Consortium"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7953152"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178964"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9052974"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2680"}],"event":{"name":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","location":"Singapore, Singapore","start":{"date-parts":[[2022,5,23]]},"end":{"date-parts":[[2022,5,27]]}},"container-title":["ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9745891\/9746004\/09746806.pdf?arnumber=9746806","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,8,15]],"date-time":"2022-08-15T16:10:32Z","timestamp":1660579832000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9746806\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,5,23]]},"references-count":31,"URL":"https:\/\/doi.org\/10.1109\/icassp43922.2022.9746806","relation":{},"subject":[],"published":{"date-parts":[[2022,5,23]]}}}