{"id":{"repo_id":"mit","oai_identifier":"oai:dspace.mit.edu:1721.1/66478"},"canonical_url":"https://search.dev.ndltd.org/etd/mit/oai:dspace.mit.edu:1721.1/66478","repository":{"repo_id":"mit","name":"MIT","base_url":"https://dspace.mit.edu/oai/request"},"display":{"title":"Unsupervised methods for speaker diarization","abstract":"Given a stream of unlabeled audio data, speaker diarization is the process of determining \"who spoke when.\" We propose a novel approach to solving this problem by taking advantage of the effectiveness of factor analysis as a front-end for extracting speaker-specific features and exploiting the inherent variabilities in the data through the use of unsupervised methods. Upon initial evaluation, our system achieves state-of-the art results of 0.9% Diarization Error Rate in the diarization of two-speaker telephone conversations. The approach is then generalized to the problem of K-speaker diarization, for which we take measures to address issues of data sparsity and experiment with the use of the von Mises-Fisher distribution for clustering on a unit hypersphere. Our extended system performs competitively on the diarization of conversations involving two or more speakers. Finally, we present promising initial results obtained from applying variational inference on our front-end speaker representation to estimate the unknown number of speakers in a given utterance.","abstract_html":"Given a stream of unlabeled audio data, speaker diarization is the process of determining "who spoke when." We propose a novel approach to solving this problem by taking advantage of the effectiveness of factor analysis as a front-end for extracting speaker-specific features and exploiting the inherent variabilities in the data through the use of unsupervised methods. Upon initial evaluation, our system achieves state-of-the art results of 0.9% Diarization Error Rate in the diarization of two-speaker telephone conversations. The approach is then generalized to the problem of K-speaker diarization, for which we take measures to address issues of data sparsity and experiment with the use of the von Mises-Fisher distribution for clustering on a unit hypersphere. Our extended system performs competitively on the diarization of conversations involving two or more speakers. Finally, we present promising initial results obtained from applying variational inference on our front-end speaker representation to estimate the unknown number of speakers in a given utterance.","abstract_has_math":false,"creators":["Shum, Stephen (Stephen Hin-Chung)"],"institution":"Massachusetts Institute of Technology","degree_name":null,"degree_level":null,"degree_discipline":null,"degree_department":"Massachusetts Institute of Technology. Dept. of Electrical Engineering and Computer Science.","school":null,"contributors":[],"advisors":["James R. Glass and Najim Dehak."],"committee_chairs":[],"committee_members":[],"year":2011,"date_issued":"2011","date_published":"2011","updated_at":"2026-07-22T22:21:59Z","subjects":["Electrical Engineering and Computer Science."],"languages":["eng"],"rights":["M.I.T. theses are protected by copyright. They may be viewed from this source for any purpose, but reproduction or distribution in any format is prohibited without written permission. See provided URL for inquiries about permission."],"rights_urls":["http://dspace.mit.edu/handle/1721.1/7582"],"identifier_entries":[]},"links":{"outbound_url":"http://hdl.handle.net/1721.1/66478","outbound_label":"Handle","outbound_source":"dc:identifier.uri"},"metadata_groups":[{"id":"people","label":"People","entries":[{"key":"dc:contributor.advisor","label":"Advisor","values":["James R. Glass and Najim Dehak."]},{"key":"dc:contributor.department","label":"Department","values":["Massachusetts Institute of Technology. Dept. of Electrical Engineering and Computer Science."]},{"key":"dc:contributor.other","label":"Dc Contributor Other","values":["Massachusetts Institute of Technology. Dept. of Electrical Engineering and Computer Science."]},{"key":"dc:creator","label":"Author","values":["Shum, Stephen (Stephen Hin-Chung)"]}]},{"id":"academic_context","label":"Academic Context","entries":[{"key":"dc:date.accessioned","label":"Dc Date Accessioned","values":["2011-10-17T21:31:07Z"]},{"key":"dc:date.available","label":"Dc Date Available","values":["2011-10-17T21:31:07Z"]},{"key":"dc:date.issued","label":"Date","values":["2011"]},{"key":"dc:publisher","label":"Institution","values":["Massachusetts Institute of Technology"]},{"key":"dc:type","label":"Dc Type","values":["Thesis"]}]},{"id":"subjects_keywords","label":"Subjects and Keywords","entries":[{"key":"dc:subject","label":"Dc Subject","values":["Electrical Engineering and Computer Science."]}]},{"id":"language_rights","label":"Language and Rights","entries":[{"key":"dc:language.iso","label":"Language (ISO)","values":["eng"]},{"key":"dc:rights","label":"Dc Rights","values":["M.I.T. theses are protected by copyright. They may be viewed from this source for any purpose, but reproduction or distribution in any format is prohibited without written permission. See provided URL for inquiries about permission."]},{"key":"dc:rights.uri","label":"Rights URI","values":["http://dspace.mit.edu/handle/1721.1/7582"]}]},{"id":"identifiers","label":"Identifiers","entries":[{"key":"dc:identifier.uri","label":"Identifier URI","values":["http://hdl.handle.net/1721.1/66478"]}]},{"id":"additional","label":"Additional Metadata","entries":[{"key":"dc:description","label":"Description","values":["Thesis (S.M.)--Massachusetts Institute of Technology, Dept. of Electrical Engineering and Computer Science, 2011.","Cataloged from PDF version of thesis.","Includes bibliographical references (p. 93-95)."]},{"key":"dc:description.abstract","label":"Abstract","values":["Given a stream of unlabeled audio data, speaker diarization is the process of determining \"who spoke when.\" We propose a novel approach to solving this problem by taking advantage of the effectiveness of factor analysis as a front-end for extracting speaker-specific features and exploiting the inherent variabilities in the data through the use of unsupervised methods. Upon initial evaluation, our system achieves state-of-the art results of 0.9% Diarization Error Rate in the diarization of two-speaker telephone conversations. The approach is then generalized to the problem of K-speaker diarization, for which we take measures to address issues of data sparsity and experiment with the use of the von Mises-Fisher distribution for clustering on a unit hypersphere. Our extended system performs competitively on the diarization of conversations involving two or more speakers. Finally, we present promising initial results obtained from applying variational inference on our front-end speaker representation to estimate the unknown number of speakers in a given utterance."]},{"key":"dc:description.degree","label":"Dc Description Degree","values":["S.M."]},{"key":"dc:title","label":"Title","values":["Unsupervised methods for speaker diarization"]}]}],"canonical_facts":{"dc:contributor.advisor":["James R. Glass and Najim Dehak."],"dc:contributor.department":["Massachusetts Institute of Technology. Dept. of Electrical Engineering and Computer Science."],"dc:contributor.other":["Massachusetts Institute of Technology. Dept. of Electrical Engineering and Computer Science."],"dc:creator":["Shum, Stephen (Stephen Hin-Chung)"],"dc:date.accessioned":["2011-10-17T21:31:07Z"],"dc:date.available":["2011-10-17T21:31:07Z"],"dc:date.issued":["2011"],"dc:description":["Thesis (S.M.)--Massachusetts Institute of Technology, Dept. of Electrical Engineering and Computer Science, 2011.","Cataloged from PDF version of thesis.","Includes bibliographical references (p. 93-95)."],"dc:description.abstract":["Given a stream of unlabeled audio data, speaker diarization is the process of determining \"who spoke when.\" We propose a novel approach to solving this problem by taking advantage of the effectiveness of factor analysis as a front-end for extracting speaker-specific features and exploiting the inherent variabilities in the data through the use of unsupervised methods. Upon initial evaluation, our system achieves state-of-the art results of 0.9% Diarization Error Rate in the diarization of two-speaker telephone conversations. The approach is then generalized to the problem of K-speaker diarization, for which we take measures to address issues of data sparsity and experiment with the use of the von Mises-Fisher distribution for clustering on a unit hypersphere. Our extended system performs competitively on the diarization of conversations involving two or more speakers. Finally, we present promising initial results obtained from applying variational inference on our front-end speaker representation to estimate the unknown number of speakers in a given utterance."],"dc:description.degree":["S.M."],"dc:identifier.uri":["http://hdl.handle.net/1721.1/66478"],"dc:language.iso":["eng"],"dc:publisher":["Massachusetts Institute of Technology"],"dc:rights":["M.I.T. theses are protected by copyright. They may be viewed from this source for any purpose, but reproduction or distribution in any format is prohibited without written permission. See provided URL for inquiries about permission."],"dc:rights.uri":["http://dspace.mit.edu/handle/1721.1/7582"],"dc:subject":["Electrical Engineering and Computer Science."],"dc:title":["Unsupervised methods for speaker diarization"],"dc:type":["Thesis"]},"updated_at":"2026-07-22T22:21:59Z"}