1852 2021 2021 eng 1079 1086 1079 - 1086 2021 conferenceobject IEEE 1 -- -- -- Speaker embeddings extracted from time delayed neural networks (TDNNs) contributed to major recent advancements in speaker recognition and verification. We use an X-Vector system trained on augmented VoxCeleb1 and VoxCeleb2 data to obtain embeddings for pathological speech after total or partial larynx removal. We show that our model is able to effectively distinguish and visualize patient groups when generating embeddings. We further compare various regression models on the task of automatically predicting different perceptual ratings by speech therapists (intelligibility, vocal effort, and overall quality) based on the extracted speaker embeddings. For both patient groups we show Pearson correlations in the range of +0.8; we find that Random Forest and Support Vector Regression produce scores that best resemble the experts' assessments. 2021 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU) 978-1-6654-3739-4 10.1109/asru51503.2021.9688278 true {"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,5,9]],"date-time":"2024-05-09T05:55:18Z","timestamp":1715234118302},"reference-count":33,"publisher":"IEEE","license":[{"start":{"date-parts":[[2021,12,13]],"date-time":"2021-12-13T00:00:00Z","timestamp":1639353600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2021,12,13]],"date-time":"2021-12-13T00:00:00Z","timestamp":1639353600000},"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":[[2021,12,13]]},"DOI":"10.1109\/asru51503.2021.9688278","type":"proceedings-article","created":{"date-parts":[[2022,2,3]],"date-time":"2022-02-03T20:31:00Z","timestamp":1643920260000},"source":"Crossref","is-referenced-by-count":1,"title":["Applying X-Vectors on Pathological Speech After Larynx Removal"],"prefix":"10.1109","author":[{"given":"Ralph","family":"Scheuerer","sequence":"first","affiliation":[{"name":"Technische Hochschule Nürnberg,Germany"}]},{"given":"Tino","family":"Haderlein","sequence":"additional","affiliation":[{"name":"Universität Erlangen-Nürnberg,Germany"}]},{"given":"Elmar","family":"Noth","sequence":"additional","affiliation":[{"name":"Universität Erlangen-Nürnberg,Germany"}]},{"given":"Tobias","family":"Bocklet","sequence":"additional","affiliation":[{"name":"Technische Hochschule Nürnberg,Germany"}]}],"member":"263","reference":[{"key":"ref33","author":"kumar","year":"2020","journal-title":"Designing neural speaker embeddings with meta learning"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461375"},{"key":"ref31","article-title":"MUSAN: A Music, Speech, and Noise Corpus","author":"snyder","year":"2015","journal-title":"ArXiv"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-2587"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1159\/000492219"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1044\/1092-4388(2007\/102)"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1044\/jshr.3402.285"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1016\/j.ijporl.2020.110191"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1121\/1.1398053"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1007\/s00268-003-7107-4"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1159\/000048592"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1007\/s00405-003-0681-0"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1016\/j.jvoice.2011.04.010"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-620"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.3389\/fninf.2021.578369"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1007\/s11136-018-2033-y"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053770"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1002\/lary.29027"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1159\/000266164"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1016\/j.csl.2021.101198"},{"key":"ref5","article-title":"Perceptual evaluation of tra-cheoesophageal speech by naive and experienced judges through the use of semantic differential scales","author":"van as","year":"2003","journal-title":"Journal of Speech Language and Hearing Research"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1016\/j.jvoice.2005.09.005"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1044\/jslhr.4303.697"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1308\/147870811X13137608455253"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1016\/S0021-9924(98)00008-2"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.3109\/14015439609099197"},{"key":"ref20","article-title":"Voxceleb: Large-scale speaker verification in the wild","author":"nagrani","year":"2019","journal-title":"Computer Science and Language"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2013-313"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU.2011.6163978"},{"key":"ref24","first-page":"6544","article-title":"Comparison of user models based on gmm-ubm and i-vectors for speech, hand-writing, and gait assessment of parkinson's disease patients","author":"vasquez-correa","year":"0","journal-title":"ICASSP 2020 — 2020 IEEE International Conference on Acoustics Speech and Signal Processing (ICASSP)"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1016\/j.jcomdis.2018.08.002"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-1431"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1266"}],"event":{"name":"2021 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","location":"Cartagena, Colombia","start":{"date-parts":[[2021,12,13]]},"end":{"date-parts":[[2021,12,17]]}},"container-title":["2021 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9687821\/9687855\/09688278.pdf?arnumber=9688278","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,5,16]],"date-time":"2022-05-16T20:42:07Z","timestamp":1652733727000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9688278\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,12,13]]},"references-count":33,"URL":"http:\/\/dx.doi.org\/10.1109\/asru51503.2021.9688278","relation":{},"subject":[],"published":{"date-parts":[[2021,12,13]]}}} proceedings-article https://doi.org/10.15223/policy-029 crossref PersonAuthorFirstName_1,PersonAuthorLastName_1,PersonAuthorFirstName_2,PersonAuthorLastName_2,PersonAuthorFirstName_3,PersonAuthorLastName_3,PersonAuthorFirstName_4,PersonAuthorLastName_4,Enrichmentconference_title,Enrichmentconference_place,PublisherName,TitleMain_1,TitleParent_1,CompletedYear,Enrichmentlocal_crossrefLicence 2021 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU) Cartagena, Colombia doi-import Begutachtet/Reviewed Ralph Scheuerer Tino Haderlein Elmar Nöth Tobias Bocklet eng uncontrolled laryngectomy eng uncontrolled intelligibility eng uncontrolled pathological speech eng uncontrolled x-vectors Fakultät Informatik Digitalisierung & Künstliche Intelligenz Zentrum für Künstliche Intelligenz (KIZ)