The effects of selected signal processing techniques on the performance of a filter-bank-based isolated word recognizer

To implement an isolated word recognizer based on filter bank techniques, decisions must be made as to how to condition the speech signal prior to the filter bank analysis (preprocessing), how to condition the feature vector at the output of the filter bank analysis (postprocessing), and how to perform the time alignment in the pattern comparison between an unknown test pattern and previously stored reference patterns (registration and distance computation). In the past most designers of such word recognition systems made arbitrary choices about how the various signal processing operations were to be carried out. This paper presents results of a systematic study of the effects of selected signal processing techniques on the performance of a filter bank isolated word recognizer using telephone-quality speech. In particular, the filter bank analyzer was a 13-channel, critical-band-spaced filter bank with excellent time resolution (impulse response durations of from 3 to 30 ms) and poor frequency selectivity (highly overlapping filters with ratios of center frequency to 3-dB bandwidth of about 8 for each band). Among the signal processing techniques studied were: preemphasis of the speech signal; time and frequency smoothing of the filter bank outputs; thresholding, quantization, and normalization of the feature vector; principal components analysis of the feature vector; local and global distance computations for use in the time alignment procedure; and noise analysis in both training and testing. Each of the signal processing techniques was studied individually; hence no tests were run in which several of the techniques were used together. Results showed that some fairly simple signal processing operations provided the best overall performance in the noise-free case; in noisy conditions performance degraded significantly for signal-to-noise ratios less than about 24 dB.