Cepstral Statistics Compensation Using Online Pseudo Stereo Codebooks for Robust Speech Recognition in Additive Noise Environments

In this paper, we propose the cepstral statistics compensation (CSC) algorithm, which alleviates the effect of additive noise on the cepstral features for speech recognition. It is a simple but quite efficient noise reduction technique that makes use of online constructed pseudo stereo codebooks. The statistics, such as mean and variance, for the cepstral features in both clean and noisy environments are evaluated using pseudo stereo codebooks. Then a transform is obtained for the noise-corrupted cepstra so that the statistics of the transformed ones are close to those of clean cepstra. Experimental results show that CSC provided a 13% reduction in word error rate when compared to the results obtained using cepstral mean and variance normalization (CMVN), and a 34% reduction in error rate compared to baseline processing in the noise range of 0-20 dB in experiments conducted on Aurora-2 test set A noisy digits database. In addition, we also provide some other noise robustness approaches based on pseudo stereo codebooks and show their effectiveness in noisy speech recognition