{"id":{"repo_id":"birmingham","oai_identifier":"oai:etheses.bham.ac.uk:596"},"canonical_url":"https://search.dev.ndltd.org/etd/birmingham/oai:etheses.bham.ac.uk:596","repository":{"repo_id":"birmingham","name":"University of Birmingham","base_url":"https://etheses.bham.ac.uk/cgi/oai2"},"display":{"title":"The role of dynamic features in speaker verification","abstract":"The thesis presents study to explore the role of dynamic features in speaker verification. Based on the theory that dynamic information should contain important speaker information, modelling the dynamics should have the potential to improve the speaker verification performance. Experiments on TD-SV using segmental hidden Markov models (SHMMs) on the YOHO database show performance improvement. However there is no significant improvement for TI-SV from experiments on the Switchboard database, using segmental GMMs. Analysis of the TD-SV results confirms that the speech dynamics modeled by SHMMs contribute more to the SV accuracy. Analysis of the TI-SV results indicates that the lack of speech dynamic information is a feature of GMM systems. It seems that the priority of the maximum likelihood training algorithm is to model stationary regions, and the role of dynamic features in GMM system, is to ensure that the classification focuses on static regions rather than to model dynamics. Study on TI-SV was carried out using conventional GMMs. Without RASTA filtering, the `delta-only' system works best. However, after RASTA filtering, the `static-plus-delta' system performs best. The results suggest that the good performance of the `delta-only' system before RASTA is mainly due to the noise robustness of the delta parameters.","abstract_html":"The thesis presents study to explore the role of dynamic features in speaker verification. Based on the theory that dynamic information should contain important speaker information, modelling the dynamics should have the potential to improve the speaker verification performance. Experiments on TD-SV using segmental hidden Markov models (SHMMs) on the YOHO database show performance improvement. However there is no significant improvement for TI-SV from experiments on the Switchboard database, using segmental GMMs. Analysis of the TD-SV results confirms that the speech dynamics modeled by SHMMs contribute more to the SV accuracy. Analysis of the TI-SV results indicates that the lack of speech dynamic information is a feature of GMM systems. It seems that the priority of the maximum likelihood training algorithm is to model stationary regions, and the role of dynamic features in GMM system, is to ensure that the classification focuses on static regions rather than to model dynamics. Study on TI-SV was carried out using conventional GMMs. Without RASTA filtering, the `delta-only' system works best. However, after RASTA filtering, the `static-plus-delta' system performs best. The results suggest that the good performance of the `delta-only' system before RASTA is mainly due to the noise robustness of the delta parameters.","abstract_has_math":false,"creators":["Liu, Ying"],"institution":"University of Birmingham","degree_name":"d_ph","degree_level":"d_ph","degree_discipline":null,"degree_department":null,"school":null,"contributors":[],"advisors":[],"committee_chairs":[],"committee_members":[],"year":2010,"date_issued":"2010-07","date_published":"2010-07","updated_at":"2026-07-24T01:11:02Z","subjects":["TK Electrical engineering. Electronics Nuclear engineering"],"languages":[],"rights":[],"rights_urls":[],"identifier_entries":[{"key":"dc:identifier.grantnumber","label":"Dc Identifier Grantnumber","values":["EOARD award FA8655-03-1-3060","EPSRC grant EP/C515986/1 \"A Unifed Model for Speech Recognition and Synthesis\"."],"render_values":[{"text":"EOARD award FA8655-03-1-3060","href":null,"code":true},{"text":"EPSRC grant EP/C515986/1 \"A Unifed Model for Speech Recognition and Synthesis\".","href":null,"code":true}]}]},"links":{"outbound_url":null,"outbound_label":null,"outbound_source":null},"metadata_groups":[{"id":"people","label":"People","entries":[{"key":"dc:contributor.sponsor","label":"Sponsor","values":["epsrc","other"]},{"key":"dc:creator","label":"Author","values":["Liu, Ying"]}]},{"id":"academic_context","label":"Academic Context","entries":[{"key":"dc:date","label":"Dc Date","values":["2010-07"]},{"key":"dc:date.issued","label":"Date","values":["2010-07"]},{"key":"dc:publisher.department","label":"Dc Publisher Department","values":["College of Engineering & Physical Sciences","School of Engineering, Department of Electronic, Electrical and Systems Engineering"]},{"key":"dc:publisher.institution","label":"Dc Publisher Institution","values":["University of Birmingham"]},{"key":"dc:relation.isreferencedby","label":"Dc Relation Isreferencedby","values":["http://etheses.bham.ac.uk//id/eprint/596/"]},{"key":"dc:type","label":"Dc Type","values":["Thesis"]},{"key":"dc:type.qualificationlevel","label":"Dc Type Qualificationlevel","values":["d_ph"]},{"key":"dc:type.qualificationname","label":"Dc Type Qualificationname","values":["d_ph"]}]},{"id":"subjects_keywords","label":"Subjects and Keywords","entries":[{"key":"dc:subject","label":"Dc Subject","values":["TK Electrical engineering. Electronics Nuclear engineering"]}]},{"id":"identifiers","label":"Identifiers","entries":[{"key":"dc:identifier.grantnumber","label":"Dc Identifier Grantnumber","values":["EOARD award FA8655-03-1-3060","EPSRC grant EP/C515986/1 \"A Unifed Model for Speech Recognition and Synthesis\"."]},{"key":"dc:identifier.uri","label":"Identifier URI","values":["http://etheses.bham.ac.uk//id/eprint/596/1/Liu10PhD.pdf","http://etheses.bham.ac.uk//id/eprint/596/2/Decl_IS_Liu10PhD.pdf"]}]},{"id":"additional","label":"Additional Metadata","entries":[{"key":"dc:description.abstract","label":"Abstract","values":["The thesis presents study to explore the role of dynamic features in speaker verification. Based on the theory that dynamic information should contain important speaker information, modelling the dynamics should have the potential to improve the speaker verification performance. Experiments on TD-SV using segmental hidden Markov models (SHMMs) on the YOHO database show performance improvement. However there is no significant improvement for TI-SV from experiments on the Switchboard database, using segmental GMMs. Analysis of the TD-SV results confirms that the speech dynamics modeled by SHMMs contribute more to the SV accuracy. Analysis of the TI-SV results indicates that the lack of speech dynamic information is a feature of GMM systems. It seems that the priority of the maximum likelihood training algorithm is to model stationary regions, and the role of dynamic features in GMM system, is to ensure that the classification focuses on static regions rather than to model dynamics. Study on TI-SV was carried out using conventional GMMs. Without RASTA filtering, the `delta-only' system works best. However, after RASTA filtering, the `static-plus-delta' system performs best. The results suggest that the good performance of the `delta-only' system before RASTA is mainly due to the noise robustness of the delta parameters."]},{"key":"dc:format","label":"Dc Format","values":["application/pdf"]},{"key":"dc:title","label":"Title","values":["The role of dynamic features in speaker verification"]}]}],"canonical_facts":{"dc:contributor.sponsor":["epsrc","other"],"dc:creator":["Liu, Ying"],"dc:date":["2010-07"],"dc:date.issued":["2010-07"],"dc:description.abstract":["The thesis presents study to explore the role of dynamic features in speaker verification. Based on the theory that dynamic information should contain important speaker information, modelling the dynamics should have the potential to improve the speaker verification performance. Experiments on TD-SV using segmental hidden Markov models (SHMMs) on the YOHO database show performance improvement. However there is no significant improvement for TI-SV from experiments on the Switchboard database, using segmental GMMs. Analysis of the TD-SV results confirms that the speech dynamics modeled by SHMMs contribute more to the SV accuracy. Analysis of the TI-SV results indicates that the lack of speech dynamic information is a feature of GMM systems. It seems that the priority of the maximum likelihood training algorithm is to model stationary regions, and the role of dynamic features in GMM system, is to ensure that the classification focuses on static regions rather than to model dynamics. Study on TI-SV was carried out using conventional GMMs. Without RASTA filtering, the `delta-only' system works best. However, after RASTA filtering, the `static-plus-delta' system performs best. The results suggest that the good performance of the `delta-only' system before RASTA is mainly due to the noise robustness of the delta parameters."],"dc:format":["application/pdf"],"dc:identifier.grantnumber":["EOARD award FA8655-03-1-3060","EPSRC grant EP/C515986/1 \"A Unifed Model for Speech Recognition and Synthesis\"."],"dc:identifier.uri":["http://etheses.bham.ac.uk//id/eprint/596/1/Liu10PhD.pdf","http://etheses.bham.ac.uk//id/eprint/596/2/Decl_IS_Liu10PhD.pdf"],"dc:publisher.department":["College of Engineering & Physical Sciences","School of Engineering, Department of Electronic, Electrical and Systems Engineering"],"dc:publisher.institution":["University of Birmingham"],"dc:relation.isreferencedby":["http://etheses.bham.ac.uk//id/eprint/596/"],"dc:subject":["TK Electrical engineering. Electronics Nuclear engineering"],"dc:title":["The role of dynamic features in speaker verification"],"dc:type":["Thesis"],"dc:type.qualificationlevel":["d_ph"],"dc:type.qualificationname":["d_ph"]},"updated_at":"2026-07-24T01:11:02Z"}