Publication
Extending previous works done on considerably smaller data sets, the paper studies linear discriminant analysis of about 30 hours of phoneme-labeled speech data in the time-frequency domain. Analysis is carried both independently in time and frequency and jointly. Data driven spectral basis show similar frequency sensitivity as human hearing. LDA-derived temporal FIR filters are consistent with temporal lateral inhibition. Considerable improvement is obtained using first temporal discriminant.
Vincent Pierre Olivier Grimaldi
Hervé Lissek, Gilles André Courtois, Vincent Pierre Olivier Grimaldi