Spectral transformations through canonical correlation analysis for speaker adptation in ASR
Khalid Choukri, Gérard Chollet, Yves Grenier · 2005
This paper describes a technique of spectral transformation for improved adaptation of a knowledge data base or reference templates to new speakers in automatic speech recognition (ASR). Based on a statistical analysis tool (Canonical correlation analysis) the proposed method permits to improve speaker independance in Large vocabulary ASR. Application to an isolated word recognizer improved a 70% correct score to 87%.