{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,22]],"date-time":"2026-04-22T19:17:45Z","timestamp":1776885465515,"version":"3.51.2"},"reference-count":56,"publisher":"IEEE","license":[{"start":{"date-parts":[[2024,12,2]],"date-time":"2024-12-02T00:00:00Z","timestamp":1733097600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,12,2]],"date-time":"2024-12-02T00:00:00Z","timestamp":1733097600000},"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":[[2024,12,2]]},"DOI":"10.1109\/slt61566.2024.10832160","type":"proceedings-article","created":{"date-parts":[[2025,1,16]],"date-time":"2025-01-16T18:31:27Z","timestamp":1737052287000},"page":"423-430","source":"Crossref","is-referenced-by-count":3,"title":["Investigation of Speaker Representation for Target-Speaker Speech Processing"],"prefix":"10.1109","author":[{"given":"Takanori","family":"Ashihara","sequence":"first","affiliation":[{"name":"NTT Corporation,Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Takafumi","family":"Moriya","sequence":"additional","affiliation":[{"name":"NTT Corporation,Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Shota","family":"Horiguchi","sequence":"additional","affiliation":[{"name":"NTT Corporation,Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Junyi","family":"Peng","sequence":"additional","affiliation":[{"name":"Brno University of Technology,Czechia"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Tsubasa","family":"Ochiai","sequence":"additional","affiliation":[{"name":"NTT Corporation,Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Marc","family":"Delcroix","sequence":"additional","affiliation":[{"name":"NTT Corporation,Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Kohei","family":"Matsuura","sequence":"additional","affiliation":[{"name":"NTT Corporation,Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hiroshi","family":"Sato","sequence":"additional","affiliation":[{"name":"NTT Corporation,Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8462661"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-1126"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2023-2280"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10095115"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP48485.2024.10447492"},{"key":"ref6","article-title":"SpeakerBeam: Speaker aware neural network for target speaker extraction in speech mixtures","author":"\u017dmol\u013akov\u00e1","year":"2019","journal-title":"JSTSP"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2017-667"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9054683"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10096478"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSPW62465.2024.10627502"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.21437\/Odyssey.2020-62"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-1602"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-856"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP48485.2024.10447653"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.21437\/CHiME.2020-9"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU57964.2023.10389625"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2010.2064307"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8462665"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461375"},{"key":"ref20","article-title":"Deep inside convolutional networks: Visualising image classification models and saliency maps","volume-title":"ICLR workshop","author":"Simonyan"},{"key":"ref21","article-title":"Understanding neural networks through deep visualization","volume-title":"ICML deep learning workshop","author":"Yosinski"},{"key":"ref22","article-title":"Explaining and harnessing adversarial examples","author":"Goodfellow","year":"2015","journal-title":"in I C L R"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1201\/9781351251389-8"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2021-1775"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-3015"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1145\/1143844.1143891"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.acl-long.580"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8683855"},{"key":"ref29","article-title":"An attention-based backend allowing efficient fine-tuning of Transformer models for speaker verification","author":"Peng","year":"2022","journal-title":"SLT"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-2650"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2842"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9414973"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-802"},{"key":"ref34","article-title":"Noncontrastive self-supervised learning of utterance-level speech representations","author":"Cho","year":"2022","journal-title":"Interspeech"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2022.3198315"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/SLT54892.2023.10022470"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSPW59220.2023.10192957"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10096915"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2022.3188113"},{"key":"ref40","article-title":"wav2vec 2.0: A framework for self-supervised learning of speech representations","author":"Baevski","year":"2020","journal-title":"NeurIPS"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3122291"},{"key":"ref42","article-title":"data2vec: A general framework for self-supervised learning in speech, vision and language","author":"Baevski","year":"2022","journal-title":"ICML"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10096626"},{"key":"ref44","article-title":"VoxSRC 2022: The fourth VoxCeleb speaker recognition challenge","author":"Huh","year":"2023","journal-title":"arXiv preprint arXiv:2302.10248"},{"key":"ref45","article-title":"VoxCeleb: Large-scale speaker verification in the wild","author":"Nagrani","year":"2019","journal-title":"Computer Speech & Language"},{"key":"ref46","article-title":"What do selfsupervised speech and speaker models learn? New findings from a cross model layer-wise analysis","author":"Ashihara","year":"2024","journal-title":"ICASSP"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00951"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178964"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9052942"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-1965"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.acl-long.80"},{"key":"ref52","article-title":"LibriMix: An opensource dataset for generalizable speech separation","author":"Cosentino","year":"2020","journal-title":"arXiv preprint arXiv:2005.11262"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2821"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2010.5495701"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2001.941023"},{"key":"ref56","article-title":"Visualizing data using t-SNE","author":"van der Maaten","year":"2008","journal-title":"JMLR"}],"event":{"name":"2024 IEEE Spoken Language Technology Workshop (SLT)","location":"Macao","start":{"date-parts":[[2024,12,2]]},"end":{"date-parts":[[2024,12,5]]}},"container-title":["2024 IEEE Spoken Language Technology Workshop (SLT)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/10830790\/10830793\/10832160.pdf?arnumber=10832160","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,1,17]],"date-time":"2025-01-17T07:50:17Z","timestamp":1737100217000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10832160\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,12,2]]},"references-count":56,"URL":"https:\/\/doi.org\/10.1109\/slt61566.2024.10832160","relation":{},"subject":[],"published":{"date-parts":[[2024,12,2]]}}}