{"id":{"repo_id":"mit","oai_identifier":"oai:dspace.mit.edu:1721.1/51651"},"canonical_url":"https://search.dev.ndltd.org/etd/mit/oai:dspace.mit.edu:1721.1/51651","repository":{"repo_id":"mit","name":"MIT","base_url":"https://dspace.mit.edu/oai/request"},"display":{"title":"Minimum cut model for spoken lecture segmentation","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_html":"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_has_math":false,"creators":["Malioutov, Igor (Igor Mikhailovich)"],"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":["Regina Barzilay."],"committee_chairs":[],"committee_members":[],"year":2007,"date_issued":"2007","date_published":"2007","updated_at":"2026-07-22T22:22:15Z","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/1721.1/51651","outbound_label":"Handle","outbound_source":"dc:identifier.uri"},"metadata_groups":[{"id":"people","label":"People","entries":[{"key":"dc:contributor.advisor","label":"Advisor","values":["Regina Barzilay."]},{"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":["Malioutov, Igor (Igor Mikhailovich)"]}]},{"id":"academic_context","label":"Academic Context","entries":[{"key":"dc:date.accessioned","label":"Dc Date Accessioned","values":["2010-02-09T16:56:45Z"]},{"key":"dc:date.available","label":"Dc Date Available","values":["2010-02-09T16:56:45Z"]},{"key":"dc:date.issued","label":"Date","values":["2007"]},{"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/1721.1/51651"]}]},{"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, February 2007.","Includes bibliographical references (leaves 129-132)."]},{"key":"dc:description.abstract","label":"Abstract","values":["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."]},{"key":"dc:description.degree","label":"Dc Description Degree","values":["S.M."]},{"key":"dc:title","label":"Title","values":["Minimum cut model for spoken lecture segmentation"]}]}],"canonical_facts":{"dc:contributor.advisor":["Regina Barzilay."],"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":["Malioutov, Igor (Igor Mikhailovich)"],"dc:date.accessioned":["2010-02-09T16:56:45Z"],"dc:date.available":["2010-02-09T16:56:45Z"],"dc:date.issued":["2007"],"dc:description":["Thesis (S.M.)--Massachusetts Institute of Technology, Dept. of Electrical Engineering and Computer Science, February 2007.","Includes bibliographical references (leaves 129-132)."],"dc:description.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."],"dc:description.degree":["S.M."],"dc:identifier.uri":["http://hdl.handle.net/1721.1/51651"],"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":["Minimum cut model for spoken lecture segmentation"],"dc:type":["Thesis"]},"updated_at":"2026-07-22T22:22:15Z"}