Cepstrum-based filter-bank design using discriminative feature extraction training at various levels

This paper investigates the realization of optimal filter bank-based cepstral parameters. The framework is the discriminative feature extraction method (DFE) which iteratively estimates the filter-bank parameters according to the errors that the system makes. Various parameters of the filter-bank, s...

Full description

Saved in:
Bibliographic Details
Main Authors: Biem, A., Katagiri, S.
Format: Conference Proceeding
Language:English
Subjects:
Applied sciences
Cepstral analysis
Cepstrum
Data mining
Exact sciences and technology
Feature extraction
Filter bank
Frequency
Humans
Information processing
Information, signal and communications theory
Nonlinear filters
Signal processing
Speech processing
Speech processing and communication systems
Speech recognition
Telecommunications and information theory
Citations: Items that cite this one
Online Access:Request full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:This paper investigates the realization of optimal filter bank-based cepstral parameters. The framework is the discriminative feature extraction method (DFE) which iteratively estimates the filter-bank parameters according to the errors that the system makes. Various parameters of the filter-bank, such as center frequency, bandwidth, and gain are optimized using a string-level optimization and a frame-level optimization scheme. Application to vowel and noisy telephone speech recognition tasks shows that the DFE method realizes a more robust classifier by appropriate feature extraction.
ISSN:1520-6149
2379-190X
DOI:10.1109/ICASSP.1997.596235