Title :
Robustness of phoneme classification in different representation spaces
Author :
Khoo, Lena ; Cvetkovic, Zoran ; Sollich, Peter
Author_Institution :
Dept. of Math., King´s Coll. London, London, UK
Abstract :
The robustness of phoneme recognition using support vector machines to additive noise is investigated for three kinds of speech representation. The representations considered are PLP, PLP with RASTA processing, and a high-dimensional principal component approximation of acoustic waveforms. While the classification in the PLP and PLP/RASTA domains attains superb accuracy on clean data, the classification in the high-dimensional space proves to be much more robust to additive noise.
Keywords :
noise; speech recognition; support vector machines; PLP/RASTA domains; additive noise; high-dimensional space; phoneme classification robustness; phoneme recognition robustness; representation spaces; speech representation; vector machines; Acoustics; Additives; Context; Europe; Noise; Speech; Support vector machines;
Conference_Titel :
Signal Processing Conference, 2006 14th European
Conference_Location :
Florence
