• Home
•  
• Call for Papers
• Paper Status
• Registration
• Workshops
• Exhibits
•  
• Technical Program
• Side Meetings
• Tutorials
• Plenaries
• Special Sessions
• Panel Sessions
• My Schedule
•  
• Practicalities
• Housing & Venue
• Special Events
• Visits
• Supporters
•  
• Contact / Discussion
• Organizing Committee
• Program Committee
• Review Committee
•  
• Related Conferences

Technical Program

Paper Detail

Paper:	SPTM-P6.2
Session:	Non-stationary Signals and Time-Frequency Analysis
Time:	Wednesday, May 17, 16:30 - 18:30
Presentation:	Poster
Topic:	Signal Processing Theory and Methods: Non-stationary Signals and Time-Frequency Analysis
Title:	MATCHING PURSUIT DECOMPOSITIONS OF NON-NOISY SPEECH SIGNALS USING SEVERAL DICTIONARIES
Authors:	Bob Sturm, Jerry Gibson, University of California, Santa Barbara, United States
Abstract:	Matching pursuit (MP) provides a way to expand signals in terms of any set of time-limited functions, or atoms, called a dictionary. These decompositions are finding use in signal analysis, coding, and enhancement. It has been shown that a dictionary should be designed carefully, but the effects of it on decomposition has not been studied in detail. We look at the effects ofdictionaries on the decomposition of speech signals using MP, by five dictionaries. We find that Gabor atoms work sufficiently well, and have fewer adverse effects in reconstruction, compared to the other dictionaries. To sound perceptually close to the original, a rate of 3000 atoms per second (aps)on average is required for the reconstruction. But at rates as low as 400 aps the signal remains intelligible. Caution is raised about the time-frequency distributions obtained by superimposing atom Wigner-Ville distributions.