Dynamic Cepstral Representations Based on Order-Dependent Windowing Methods

摘要

In this paper, we propose dynamic cepstral rep- resentations to effectively capture the temporal information of cepstral coefficients. The number of speech frames for the regres- sion analysis to extract a dynamic cepstral coefficient is inversely proportional to the cepstral order since the cepstral coefficients of higher orders are more fluctuating than those of lower or- ders. By exploiting the relationship between the window length for extracting a dynamic cepstral coefficient an the statistical variance of the cepstral coefficient, we propose three kinds of windowing methods in this work: an utterance-specific variance- ratio windowing method, a statistical variance-ratio windowing method, and an inverse-lifter windowing method.