ISCA Tutorial and Research Workshop on Statistical and Perceptual Audio Processing ICC Jeju, Korea October 3, 2004

Stochastic Techniques in Deriving Perceptual Knowledge

Hynek Hermansky

IDIAP Research Institute, Martigny, Switzerland

The paper argues on examples of selected past works that stochastic and knowledge-based approaches to automatic speech recognition do not contradict each other. Frequency resolution of human hearing decreases with increasing frequency. Spectral basis designed for optimal discrimination among different phonemes of speech have similar property. Further, human hearing is most sensitive to modulations with frequency around 4 Hz. Filters on feature trajectories, designed for optimal discrimination among phonemes of speech are bandpass with central frequency around 4 Hz.

Full Paper

Bibliographic reference.  Hermansky, Hynek (2004): "Stochastic techniques in deriving perceptual knowledge", In SAPA-2004, paper 136.