Improvement in Speech Recognition Performance using Beamforming based Speech Enhancement

Abstract — The speech, being a fundamental way of communication for the humans, has been embedded in various essential applications like speech recognition, voicedistance- talk and other forms of personal communications. There are so many applications of speech still to be far from reality just because of lack of efficient and reliable noise removal mechanism and techniques for preserving or improving the intelligibility for the speech signals. The broad categories of speech enhancement techniques can be listed as speech filtering techniques, beam forming techniques and active noise cancellation methods. In this paper, our work has two-fold objective. First is to improve the speech recognition performance in multi-microphone environment. Second, we attempted to analyze the performance of speech recognition against the filter-bank parameters; filter length and number of subbands. The experiments were performed for 20 words including numbers and commands, 10 words of numbers only and 10 words of commands only for different values of filter bank parameters. The results obtained have proved the speech enhancing capability of the beamforming technique in multi-microphone network where noise and echo-interference can degrade the original speech signal.