Noise Reduction Algorithm for Robust Speech Recognition Using Minimum Statistics Method and Neural Network VAD

In this paper we present basic ideas of noise reduction for robust speech recognition using minimum statistic algorithm and VAD based on neural networks. Noise estimation is based on minimum statistic procedure and noise subtraction in spectral space is performed based on neural network VAD output. For noise subtraction two different subtraction factors are used. If VAD output indicates noise frame, subtraction is carried out with one subtraction factor. On the other hand if VAD output value indicates speech frame, than subtraction with the other subtraction factor is carried out. Research and tests have been performed on German part of Aurora3 database. Performance was tested according to ETSI ES 201/108 standard. During testing several combinations of parameters have been experimented and optimum values were defined.