2026-09-19T05:39:15Zhttps://dspace.mit.edu/server/oai/requestoai:dspace.mit.edu:1721.1/516512022-01-13T07:54:29Zcom_1721.1_7582com_1721.1_7581col_1721.1_131023
Regina Barzilay.
Malioutov, Igor (Igor Mikhailovich)
Massachusetts Institute of Technology. Dept. of Electrical Engineering and Computer Science.
Massachusetts Institute of Technology. Department of Electrical Engineering and Computer Science
2010-02-09T16:56:45Z
2010-02-09T16:56:45Z
2006
2007
http://hdl.handle.net/1721.1/51651
500912209
Thesis (S.M.)--Massachusetts Institute of Technology, Dept. of Electrical Engineering and Computer Science, February 2007.
Includes bibliographical references (leaves 129-132).
We introduce a novel unsupervised algorithm for text segmentation. We re-conceptualize text segmentation as a graph-partitioning task aiming to optimize the normalized-cut criterion. Central to this framework is a contrastive analysis of lexical distribution that simultaneously optimizes the total similarity within each segment and dissimilarity across segments. Our experimental results show that the normalized-cut algorithm obtains performance improvements over the state-of-the-art techniques on the task of spoken lecture segmentation. Another attractive property of the algorithm is robustness to noise. The accuracy of our algorithm does not deteriorate significantly when applied to automatically recognized speech. The impact of the novel segmentation framework extends beyond the text segmentation domain. We demonstrate the power of the model by applying it to the segmentation of raw acoustic signal without intermediate speech recognition.
by Igor Malioutov.
S.M.
132 leaves
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.
Minimum cut model for spoken lecture segmentation
Thesis
application/pdf
Publication
unknown
unknown
<Publication xmlns="https://www.openaire.eu/cerif-profile/1.1/" id="d6b600ad-527c-41b0-8844-c82e2c26a622">
<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>Minimum cut model for spoken lecture segmentation</Title>
<PublishedIn>
<Publication>
</Publication>
</PublishedIn>
<PublicationDate>2007</PublicationDate>
<Authors>
<Author>
<DisplayName>Malioutov, Igor (Igor Mikhailovich)</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>We introduce a novel unsupervised algorithm for text segmentation. We re-conceptualize text segmentation as a graph-partitioning task aiming to optimize the normalized-cut criterion. Central to this framework is a contrastive analysis of lexical distribution that simultaneously optimizes the total similarity within each segment and dissimilarity across segments. Our experimental results show that the normalized-cut algorithm obtains performance improvements over the state-of-the-art techniques on the task of spoken lecture segmentation. Another attractive property of the algorithm is robustness to noise. The accuracy of our algorithm does not deteriorate significantly when applied to automatically recognized speech. The impact of the novel segmentation framework extends beyond the text segmentation domain. We demonstrate the power of the model by applying it to the segmentation of raw acoustic signal without intermediate speech recognition.</Abstract>
<Access xmlns="http://purl.org/coar/access_right"
>
</Access>
</Publication>