Title :
Improving automatic phoneme alignment under noisy conditions by incorporating spectral voicing information
Author :
Jancovic, P. ; Kokuer, Munevver
Author_Institution :
Sch. of Electron., Electr. & Comput. Eng., Univ. of Birmingham, Birmingham
Abstract :
An incorporation of spectral voicing information of speech signal for improving the accuracy of automatic phoneme alignment under noisy conditions is presented. Experiments are conducted on the TIMIT speech corpus corrupted by an additive noise at various signal-to-noise ratios. Significant performance improvements are reported.
Keywords :
speech processing; speech recognition; additive noise; automatic phoneme alignment; spectral voicing information; speech signal;
Journal_Title :
Electronics Letters
DOI :
10.1049/el.2009.0715
