Mandarin speech recognition using segment-basedcepstral comparison in noisy conditions
Shin-Lun Tung, Yau‐Tarng Juang · Electronics Letters · 1996
A new scheme is proposed that compensates for the effects of noise in speech recognition systems. The new scheme was applied to Mandarin speech recognition. Another scheme, based on interpolation of the compensation vectors of several environments for a particular environment that is not obtained during the training phase, called interpolated SSDCN (ISSDCN), is also presented. Experimental results show that the scheme performs well under different SNR conditions.