{"id":{"repo_id":"uno","oai_identifier":"oai:scholarworks.uno.edu:td-1051"},"canonical_url":"https://search.dev.ndltd.org/etd/uno/oai:scholarworks.uno.edu:td-1051","repository":{"repo_id":"uno","name":"University of New Orleans","base_url":"https://scholarworks.uno.edu/do/oai/"},"display":{"title":"Novel Pitch Detection Algorithm With Application to Speech Coding","abstract":"This thesis introduces a novel method for accurate pitch detection and speech segmentation, named Multi-feature, Autocorrelation (ACR) and Wavelet Technique (MAWT). MAWT uses feature extraction, and ACR applied on Linear Predictive Coding (LPC) residuals, with a wavelet-based refinement step. MAWT opens the way for a unique approach to modeling: although speech is divided into segments, the success of voicing decisions is not crucial. Experiments demonstrate the superiority of MAWT in pitch period detection accuracy over existing methods, and illustrate its advantages for speech segmentation. These advantages are more pronounced for gain-varying and transitional speech, and under noisy conditions.","abstract_html":"This thesis introduces a novel method for accurate pitch detection and speech segmentation, named Multi-feature, Autocorrelation (ACR) and Wavelet Technique (MAWT). MAWT uses feature extraction, and ACR applied on Linear Predictive Coding (LPC) residuals, with a wavelet-based refinement step. MAWT opens the way for a unique approach to modeling: although speech is divided into segments, the success of voicing decisions is not crucial. Experiments demonstrate the superiority of MAWT in pitch period detection accuracy over existing methods, and illustrate its advantages for speech segmentation. These advantages are more pronounced for gain-varying and transitional speech, and under noisy conditions.","abstract_has_math":false,"creators":["Kura, Vijay"],"institution":null,"degree_name":"M.S.","degree_level":"Thesis","degree_discipline":"Electrical Engineering","degree_department":null,"school":null,"contributors":["Charalmpidis, Dimitrios","Ma, Jing","Jilkov, Vesselin"],"advisors":[],"committee_chairs":[],"committee_members":[],"year":2003,"date_issued":"2003-12-19T08:00:00Z","date_published":"2003-12-19T08:00:00Z","updated_at":"2026-07-24T05:27:57Z","subjects":["fundamental frequency","speech coding","wavelets and linear predictive coding"],"languages":[],"rights":[],"rights_urls":[],"identifier_entries":[]},"links":{"outbound_url":"https://scholarworks.uno.edu/td/52","outbound_label":"Repository record","outbound_source":"dc:identifier"},"metadata_groups":[{"id":"people","label":"People","entries":[{"key":"dc:contributor","label":"Contributor","values":["Charalmpidis, Dimitrios","Ma, Jing","Jilkov, Vesselin"]},{"key":"dc:creator","label":"Author","values":["Kura, Vijay"]}]},{"id":"academic_context","label":"Academic Context","entries":[{"key":"thesis:degree_discipline","label":"Discipline","values":["Electrical Engineering"]},{"key":"thesis:degree_level","label":"Degree Level","values":["Thesis"]},{"key":"thesis:degree_name","label":"Degree Name","values":["M.S."]}]},{"id":"subjects_keywords","label":"Subjects and Keywords","entries":[{"key":"dc:subject","label":"Dc Subject","values":["fundamental frequency","speech coding","wavelets and linear predictive coding"]}]},{"id":"identifiers","label":"Identifiers","entries":[{"key":"dc:identifier","label":"Identifier","values":["https://scholarworks.uno.edu/td/52"]}]},{"id":"additional","label":"Additional Metadata","entries":[{"key":"dc:description.abstract","label":"Abstract","values":["This thesis introduces a novel method for accurate pitch detection and speech segmentation, named Multi-feature, Autocorrelation (ACR) and Wavelet Technique (MAWT). MAWT uses feature extraction, and ACR applied on Linear Predictive Coding (LPC) residuals, with a wavelet-based refinement step. MAWT opens the way for a unique approach to modeling: although speech is divided into segments, the success of voicing decisions is not crucial. Experiments demonstrate the superiority of MAWT in pitch period detection accuracy over existing methods, and illustrate its advantages for speech segmentation. These advantages are more pronounced for gain-varying and transitional speech, and under noisy conditions."]},{"key":"dc:title","label":"Title","values":["Novel Pitch Detection Algorithm With Application to Speech Coding"]}]}],"canonical_facts":{"dc:contributor":["Charalmpidis, Dimitrios","Ma, Jing","Jilkov, Vesselin"],"dc:creator":["Kura, Vijay"],"dc:description.abstract":["This thesis introduces a novel method for accurate pitch detection and speech segmentation, named Multi-feature, Autocorrelation (ACR) and Wavelet Technique (MAWT). MAWT uses feature extraction, and ACR applied on Linear Predictive Coding (LPC) residuals, with a wavelet-based refinement step. MAWT opens the way for a unique approach to modeling: although speech is divided into segments, the success of voicing decisions is not crucial. Experiments demonstrate the superiority of MAWT in pitch period detection accuracy over existing methods, and illustrate its advantages for speech segmentation. These advantages are more pronounced for gain-varying and transitional speech, and under noisy conditions."],"dc:identifier":["https://scholarworks.uno.edu/td/52"],"dc:subject":["fundamental frequency","speech coding","wavelets and linear predictive coding"],"dc:title":["Novel Pitch Detection Algorithm With Application to Speech Coding"],"thesis:degree_discipline":["Electrical Engineering"],"thesis:degree_level":["Thesis"],"thesis:degree_name":["M.S."]},"updated_at":"2026-07-24T05:27:57Z"}