Novel Pitch Detection Algorithm With Application to Speech Coding

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. MAW...

Full description

Bibliographic Details
Main Author:	Kura, Vijay
Format:	Others
Published:	ScholarWorks@UNO 2003
Subjects:	fundamental frequency speech coding wavelets and linear predictive coding
Online Access:	http://scholarworks.uno.edu/td/52 http://scholarworks.uno.edu/cgi/viewcontent.cgi?article=1051&context=td

id	ndltd-uno.edu-oai-scholarworks.uno.edu-td-1051
record_format	oai_dc
spelling	ndltd-uno.edu-oai-scholarworks.uno.edu-td-10512016-10-21T17:03:33Z Novel Pitch Detection Algorithm With Application to Speech Coding Kura, Vijay 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. 2003-12-19T08:00:00Z text application/pdf http://scholarworks.uno.edu/td/52 http://scholarworks.uno.edu/cgi/viewcontent.cgi?article=1051&context=td University of New Orleans Theses and Dissertations ScholarWorks@UNO fundamental frequency speech coding wavelets and linear predictive coding
collection	NDLTD
format	Others
sources	NDLTD
topic	fundamental frequency speech coding wavelets and linear predictive coding
spellingShingle	fundamental frequency speech coding wavelets and linear predictive coding Kura, Vijay Novel Pitch Detection Algorithm With Application to Speech Coding
description	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.
author	Kura, Vijay
author_facet	Kura, Vijay
author_sort	Kura, Vijay
title	Novel Pitch Detection Algorithm With Application to Speech Coding
title_short	Novel Pitch Detection Algorithm With Application to Speech Coding
title_full	Novel Pitch Detection Algorithm With Application to Speech Coding
title_fullStr	Novel Pitch Detection Algorithm With Application to Speech Coding
title_full_unstemmed	Novel Pitch Detection Algorithm With Application to Speech Coding
title_sort	novel pitch detection algorithm with application to speech coding
publisher	ScholarWorks@UNO
publishDate	2003
url	http://scholarworks.uno.edu/td/52 http://scholarworks.uno.edu/cgi/viewcontent.cgi?article=1051&context=td
work_keys_str_mv	AT kuravijay novelpitchdetectionalgorithmwithapplicationtospeechcoding
_version_	1718387770582368256

Novel Pitch Detection Algorithm With Application to Speech Coding

Similar Items