Comparing Jacobian adaptation with cepstral mean normalization and parallel model combination for noise robust speech recognition

摘要

In this paper, two techniques are researched for Jacobian adaptation (JA) in the presence of additive noise. Since the original concept of JA was presented only for static cepstral coefficients, the performance of JA is researched when it is extended to cover also the delta cepstrum. However, this extension or the original concept can not provide accurate recognition performance when the mismatch between the training and recognition environments is out of the linear range of JA. Hence, this problem can be alleviated to some extent by dividing JA into two steps. At first, the adaptation is done e.g. from clean to the target environment having "high" SNR level. After that, the new JA matrices are calculated and they are used in the second step to adapt the system to the lower target SNR level. Both of the above adaptation methods have been compared to cepstral mean normalization (CMN) and parallel model combination (PMC) in an isolated word recognition task having a vocabulary of 200 English words. The best performance was achieved with PMC but JA showed comparable performance to CMN and outperformed it when JA was done in two steps from SNR of 25 dB to 5 dB. The system was tested with the SpeechDat(II) database by adding noise recorded inside a car to the test set utterances at various SNR levels.