{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,27]],"date-time":"2026-05-27T06:06:06Z","timestamp":1779861966706,"version":"3.53.1"},"reference-count":40,"publisher":"IEEE","license":[{"start":{"date-parts":[[2023,1,9]],"date-time":"2023-01-09T00:00:00Z","timestamp":1673222400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,1,9]],"date-time":"2023-01-09T00:00:00Z","timestamp":1673222400000},"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":[[2023,1,9]]},"DOI":"10.1109\/slt54892.2023.10022350","type":"proceedings-article","created":{"date-parts":[[2023,1,27]],"date-time":"2023-01-27T13:54:03Z","timestamp":1674827643000},"page":"428-435","source":"Crossref","is-referenced-by-count":8,"title":["Joint Optimization of Diffusion Probabilistic-Based Multichannel Speech Enhancement with Far-Field Speaker Verification"],"prefix":"10.1109","author":[{"given":"Sandipana","family":"Dowerah","sequence":"first","affiliation":[{"name":"Université de Lorraine, CNRS,Nancy,France,F-54000"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Romain","family":"Serizel","sequence":"additional","affiliation":[{"name":"Université de Lorraine, CNRS,Nancy,France,F-54000"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Denis","family":"Jouvet","sequence":"additional","affiliation":[{"name":"Université de Lorraine, CNRS,Nancy,France,F-54000"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Mohammad","family":"Mohammadamini","sequence":"additional","affiliation":[{"name":"University of Avignon,Laboratoire Informatique d'Avignon,France"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Driss","family":"Matrouf","sequence":"additional","affiliation":[{"name":"University of Avignon,Laboratoire Informatique d'Avignon,France"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"crossref","DOI":"10.21437\/Odyssey.2020-26","article-title":"Deep speaker em-beddings for far- field speaker recognition on short utter-ances","author":"Gusev","year":"2020","journal-title":"Odyssey"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-1435"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-2650"},{"key":"ref4","article-title":"X-vectors: Robust dnn em-beddings for speaker recognition","author":"Snyder","year":"2018","journal-title":"ICASSP"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-1837"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-1249"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2013-130"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2014.2352935"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3092838"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2016.7471664"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2018-2196"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/icassp.2019.8683294"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-1356"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-1428"},{"key":"ref15","article-title":"Dereverberation and beamforming in far-field speaker recognition","author":"Mosner","year":"2018","journal-title":"ICASSP"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-1496"},{"key":"ref17","doi-asserted-by":"crossref","DOI":"10.21437\/Odyssey.2020-65","article-title":"Robust speaker recognition using speech enhancement and at-tention model","author":"Shi","year":"2020","journal-title":"Odyssey"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2007.902460"},{"key":"ref19","article-title":"Denoising dif-fusion probabilistic models","author":"Ho","year":"2020","journal-title":"ArXiv"},{"key":"ref20","article-title":"Grad-tts: A diffusion probabilistic model for text-to-speech","author":"Popov","year":"2021","journal-title":"ICML"},{"key":"ref21","article-title":"Deep unsupervised learning using nonequilibrium thermodynamics","author":"Sohl-Dickstein","year":"2015","journal-title":"MLR"},{"key":"ref22","article-title":"A study on speech enhancement based on diffusion probabilistic model","author":"Lu","year":"2021","journal-title":"APSIPAASC"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9746901"},{"key":"ref24","article-title":"Maximum likelihood training of score-based dif-fusion models","author":"Song","year":"2021","journal-title":"NeurIPS"},{"key":"ref25","article-title":"Deep unsupervised learning using nonequilibrium thermodynamics","author":"Sohl-Dickstein","year":"2015","journal-title":"ICML"},{"key":"ref26","article-title":"Wavegrad: Es-timating gradients for waveform generation","author":"Chen","year":"2021","journal-title":"ICLR"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-24574-4_28"},{"key":"ref28","article-title":"Generative modeling by estimating gradients of the data distribution","author":"Song","year":"2019","journal-title":"NeurIPS"},{"key":"ref29","article-title":"Improved techniques for training score-based generative models","author":"Song","year":"2020","journal-title":"NeurIPS"},{"key":"ref30","article-title":"Score-based generative modeling through stochastic differential equations","author":"Song","year":"2020","journal-title":"ICLR"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1017\/S0334270000001405"},{"key":"ref32","article-title":"Score-based generative modeling through stochastic differential equations","author":"Song","year":"2020","journal-title":"ICLR"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1503.02531"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00145"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178964"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.63317\/27f7xn42hpjt"},{"key":"ref37","article-title":"Freesound datasets: A platform for the creation of open audio datasets","author":"Fonseca","year":"2017","journal-title":"ISMIR"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461310"},{"key":"ref39","article-title":"Bootstrap estimates for con-fidence intervals in asr performance evaluation","author":"Bisani","year":"2004","journal-title":"ICASSP"},{"key":"ref40","article-title":"Compensating noise and reverberation in far-field Multichannel Speaker Veri-fication","author":"Dowerah","year":"2022","journal-title":"working paper or preprint"}],"event":{"name":"2022 IEEE Spoken Language Technology Workshop (SLT)","location":"Doha, Qatar","start":{"date-parts":[[2023,1,9]]},"end":{"date-parts":[[2023,1,12]]}},"container-title":["2022 IEEE Spoken Language Technology Workshop (SLT)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/10022052\/10022330\/10022350.pdf?arnumber=10022350","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,27]],"date-time":"2026-05-27T05:41:28Z","timestamp":1779860488000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10022350\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,1,9]]},"references-count":40,"URL":"https:\/\/doi.org\/10.1109\/slt54892.2023.10022350","relation":{},"subject":[],"published":{"date-parts":[[2023,1,9]]}}}