{"id":{"repo_id":"mit","oai_identifier":"oai:dspace.mit.edu:1721.1/44367"},"canonical_url":"https://search.dev.ndltd.org/etd/mit/oai:dspace.mit.edu:1721.1/44367","repository":{"repo_id":"mit","name":"MIT","base_url":"https://dspace.mit.edu/oai/request"},"display":{"title":"Large-margin Gaussian mixture modeling for automatic speech recognition","abstract":"Discriminative training for acoustic models has been widely studied to improve the performance of automatic speech recognition systems. To enhance the generalization ability of discriminatively trained models, a large-margin training framework has recently been proposed. This work investigates large-margin training in detail, integrates the training with more flexible classifier structures such as hierarchical classifiers and committee-based classifiers, and compares the performance of the proposed modeling scheme with existing discriminative methods such as minimum classification error (MCE) training. Experiments are performed on a standard phonetic classification task and a large vocabulary speech recognition (LVCSR) task. In the phonetic classification experiments, the proposed modeling scheme yields about 1.5% absolute error reduction over the current state of the art. In the LVCSR experiments on the MIT lecture corpus, the large-margin model has about 6.0% absolute word error rate reduction over the baseline model and about 0.6% absolute error rate reduction over the MCE model.","abstract_html":"Discriminative training for acoustic models has been widely studied to improve the performance of automatic speech recognition systems. To enhance the generalization ability of discriminatively trained models, a large-margin training framework has recently been proposed. This work investigates large-margin training in detail, integrates the training with more flexible classifier structures such as hierarchical classifiers and committee-based classifiers, and compares the performance of the proposed modeling scheme with existing discriminative methods such as minimum classification error (MCE) training. Experiments are performed on a standard phonetic classification task and a large vocabulary speech recognition (LVCSR) task. In the phonetic classification experiments, the proposed modeling scheme yields about 1.5% absolute error reduction over the current state of the art. In the LVCSR experiments on the MIT lecture corpus, the large-margin model has about 6.0% absolute word error rate reduction over the baseline model and about 0.6% absolute error rate reduction over the MCE model.","abstract_has_math":false,"creators":["Chang, Hung-An, Ph. D. Massachusetts Institute of Technology"],"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."],"committee_chairs":[],"committee_members":[],"year":2008,"date_issued":"2008","date_published":"2008","updated_at":"2026-07-22T22:21:48Z","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/1721.1/44367","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."]},{"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":["Chang, Hung-An, Ph. D. Massachusetts Institute of Technology"]}]},{"id":"academic_context","label":"Academic Context","entries":[{"key":"dc:date.accessioned","label":"Dc Date Accessioned","values":["2009-01-30T16:37:50Z"]},{"key":"dc:date.available","label":"Dc Date Available","values":["2009-01-30T16:37:50Z"]},{"key":"dc:date.issued","label":"Date","values":["2008"]},{"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/1721.1/44367"]}]},{"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, 2008.","Includes bibliographical references (p. 101-103)."]},{"key":"dc:description.abstract","label":"Abstract","values":["Discriminative training for acoustic models has been widely studied to improve the performance of automatic speech recognition systems. To enhance the generalization ability of discriminatively trained models, a large-margin training framework has recently been proposed. This work investigates large-margin training in detail, integrates the training with more flexible classifier structures such as hierarchical classifiers and committee-based classifiers, and compares the performance of the proposed modeling scheme with existing discriminative methods such as minimum classification error (MCE) training. Experiments are performed on a standard phonetic classification task and a large vocabulary speech recognition (LVCSR) task. In the phonetic classification experiments, the proposed modeling scheme yields about 1.5% absolute error reduction over the current state of the art. In the LVCSR experiments on the MIT lecture corpus, the large-margin model has about 6.0% absolute word error rate reduction over the baseline model and about 0.6% absolute error rate reduction over the MCE model."]},{"key":"dc:description.degree","label":"Dc Description Degree","values":["S.M."]},{"key":"dc:title","label":"Title","values":["Large-margin Gaussian mixture modeling for automatic speech recognition"]}]}],"canonical_facts":{"dc:contributor.advisor":["James R. Glass."],"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":["Chang, Hung-An, Ph. D. Massachusetts Institute of Technology"],"dc:date.accessioned":["2009-01-30T16:37:50Z"],"dc:date.available":["2009-01-30T16:37:50Z"],"dc:date.issued":["2008"],"dc:description":["Thesis (S.M.)--Massachusetts Institute of Technology, Dept. of Electrical Engineering and Computer Science, 2008.","Includes bibliographical references (p. 101-103)."],"dc:description.abstract":["Discriminative training for acoustic models has been widely studied to improve the performance of automatic speech recognition systems. To enhance the generalization ability of discriminatively trained models, a large-margin training framework has recently been proposed. This work investigates large-margin training in detail, integrates the training with more flexible classifier structures such as hierarchical classifiers and committee-based classifiers, and compares the performance of the proposed modeling scheme with existing discriminative methods such as minimum classification error (MCE) training. Experiments are performed on a standard phonetic classification task and a large vocabulary speech recognition (LVCSR) task. In the phonetic classification experiments, the proposed modeling scheme yields about 1.5% absolute error reduction over the current state of the art. In the LVCSR experiments on the MIT lecture corpus, the large-margin model has about 6.0% absolute word error rate reduction over the baseline model and about 0.6% absolute error rate reduction over the MCE model."],"dc:description.degree":["S.M."],"dc:identifier.uri":["http://hdl.handle.net/1721.1/44367"],"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":["Large-margin Gaussian mixture modeling for automatic speech recognition"],"dc:type":["Thesis"]},"updated_at":"2026-07-22T22:21:48Z"}