A Performance Analysis of Features from Complex Cepstra of Warped DST, DCT and DHT Filters for Phoneme Recognition

An analytical model has been developed for the warped discrete Hartley transform cepstrum (WDHTC) in a recent work. Along similar lines, the warped discrete cosine transform (WDCT) has since been modelled in a companion paper. These were preceded by empirical studies of the WDCT cepstrum (WDCTC) as applied to speech feature extraction for vowel recognition and speaker identification. In this paper, we derive the theoretical complex cepstrum (TCC) based on the warped discrete sine transform. We argue that the common recipe evolved through these papers may be used as a measure to compare analytically deducible front- end speech recognition schemes. In particular, we show that the WDCTC-based scheme outperforms the present warped discrete sine transform cepstrum (WDSTC)-based scheme and the one based on warped discrete Hartley transform in terms of low variance of features due to reduced spectral dynamic range. Phoneme recognition performance of WDCTC,WDHTC and WDSTC corroborate well with our analytical findings.