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. 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.

Name thesis:degree_name

M.S.

Level thesis:degree_level

Thesis

Discipline thesis:degree_discipline

Electrical Engineering

Year

2003

Author dc:creator

• Kura, Vijay

Contributors dc:contributor

• Charalmpidis, Dimitrios
• Ma, Jing
• Jilkov, Vesselin

• fundamental frequency
• speech coding
• wavelets and linear predictive coding

Repository record dc:identifier

https://scholarworks.uno.edu/td/52

OAI identifier oai:identifier

oai:scholarworks.uno.edu:td-1051