Comparison of Parametric Representations for Monosyllabic Word Recognition in Continuously Spoken Sentences

o Several parametric representations of the acoustic signal were compared as to word recognition performance in a syllableoriented continuous speech recognition system. The vocabulary included many phonetically similar monosyllabic words, therefore the emphasis was on ability to retain phonetically significant acoustic information in the face of syntactic and duration variations. For each ~ arameter set (based on a mel-frequency cepstrum, a linear frequency cepstrum, a linear prediction cepstrum, a linear prediction spectrum, or a set of reflection coefficients), word templates were generated using an efficient dynamic method, and test data were time registered wi th the templates. A set of ten melfrequency cepstrum coefficients computed every 6" 4 ms resulted in the best performance, namely 96 .. 5% and 9500% recognition with each of two speakers.. The superior performance of the mel-frequency cepstrum coefficients may be attributed to the fact that they better represent the perceptually relevant aspects of the short-term speech spectrum ..