Dynamic Cepstral Representations Based on Order-Dependent Windowing Methods

Hong Kook KIM  Seung Ho CHOI  Hwang Soo LEE  

IEICE TRANSACTIONS on Information and Systems   Vol.E81-D   No.5   pp.434-440
Publication Date: 1998/05/25
Online ISSN: 
Print ISSN: 0916-8532
Type of Manuscript: PAPER
Category: Speech Processing and Acoustics
cepstrum,  dynamic cepstrum,  order-dependent windowing,  speech recognition,  

Full Text: PDF>>
Buy this Article

In this paper, we propose dynamic cepstral representations to effectively capture the temporal information of cepstral coefficients. The number of speech frames for the regression 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 orders. By exploiting the relationship between the window length for extracting a dynamic cepstral coefficient and 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. Intra-speaker, inter-speaker, and speaker-independent recognition tests on 100 phonetically balanced words are carried out to evaluate the performance of the proposed order-dependent windowing methods.