Noisy speech recognition using blind spatial subtraction array technique and deep bottleneck features

In this study, we investigate the effect of blind spatial subtraction arrays (BSSA) on speech recognition systems by comparing the performance of a method using Mel-Frequency Cepstral Coefficients (MFCCs) with a method using Deep Bottleneck Features (DBNF) based on Deep Neural Networks (DNN). Performance is evaluated under various conditions, including noisy, in-vehicle conditions. Although performance of the DBNF-based system was much more degraded by noise than the MFCC-based system, BSSA improved the performance of both methods greatly, especially when matched condition training of acoustic models was employed. These results show the effectiveness of BSSA for speech recognition.