Precise Voicing Information Extraction in Speech Signals Using the Analytic Signal

Stéphane Rossignol (1) , Olivier Pietquin (1)

1 SUPELEC-Campus Metz

This paper proposes a voiced – unvoiced measure based on the Analytic Signal computation. This voiced – unvoiced feature can be useful for many speech processing applications. For instance, considering speech recognition, it could be incorporated into commonly used acoustic feature vectors, such as for example the Mel Frequency Cepstral Coefficients (MFCC)

Domains: Engineering Sciences [physics]; Acoustics [physics.class-ph]; Physics [physics]; Mechanics [physics]; Acoustics [physics.class-ph]

Stéphane Rossignol, Olivier Pietquin. Precise Voicing Information Extraction in Speech Signals Using the Analytic Signal. ISSPIT 2008, Dec 2008, Sarajevo, Bosnia and Herzegovina. pp.207-212, ⟨10.1109/ISSPIT.2008.4775673⟩. ⟨hal-00351273⟩