2026-09-19T03:56:31Zhttps://dspace.mit.edu/server/oai/requestoai:dspace.mit.edu:1721.1/664782022-01-13T07:54:29Zcom_1721.1_7582com_1721.1_7581col_1721.1_131023
James R. Glass and Najim Dehak.
Shum, Stephen (Stephen Hin-Chung)
Massachusetts Institute of Technology. Dept. of Electrical Engineering and Computer Science.
Massachusetts Institute of Technology. Department of Electrical Engineering and Computer Science
2011-10-17T21:31:07Z
2011-10-17T21:31:07Z
2011
2011
http://hdl.handle.net/1721.1/66478
756462731
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).
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.
by Stephen Shum.
S.M.
95 p.
eng
Massachusetts Institute of Technology
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.
http://dspace.mit.edu/handle/1721.1/7582
Electrical Engineering and Computer Science.
Unsupervised methods for speaker diarization
Thesis
application/pdf
false
Publication
unknown
unknown
<Publication xmlns="https://www.openaire.eu/cerif-profile/1.1/" id="af3b5545-77c2-4473-8d4e-6afc33c19117">
<Type xmlns="https://www.openaire.eu/cerif-profile/vocab/COAR_Publication_Types">http://purl.org/coar/resource_type/c_1843</Type>
<Language>eng</Language>
<Title>Unsupervised methods for speaker diarization</Title>
<PublishedIn>
<Publication>
</Publication>
</PublishedIn>
<PublicationDate>2011</PublicationDate>
<Authors>
<Author>
<DisplayName>Shum, Stephen (Stephen Hin-Chung)</DisplayName>
<Affiliation>
<OrgUnit>
</OrgUnit>
</Affiliation>
</Author>
</Authors>
<Editors>
</Editors>
<Publishers>
<Publisher>
<DisplayName>Massachusetts Institute of Technology</DisplayName>
<OrgUnit />
</Publisher>
</Publishers>
<License>http://dspace.mit.edu/handle/1721.1/7582</License>
<Keyword>Electrical Engineering and Computer Science.</Keyword>
<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>
<Access xmlns="http://purl.org/coar/access_right"
>
</Access>
</Publication>