Subband analysis for robust speech recognition in the presence of car noise

Date
1995-05
Advisor
Supervisor
Co-Advisor
Co-Supervisor
Instructor
Source Title
IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP 1995
Print ISSN
0736-7791
Electronic ISSN
Publisher
IEEE
Volume
Issue
Pages
417 - 420
Language
English
Type
Conference Paper
Journal Title
Journal ISSN
Volume Title
Series
Abstract

In this paper, a new set of speech feature representations for robust speech recognition in the presence of car noise are proposed. These parameters are based on subband analysis of the speech signal. Line Spectral Frequency (LSF) representation of the Linear Prediction (LP) analysis in subbands and cepstral coefficients derived from subband analysis (SUBCEP) are introduced, and the performances of the new feature representations are compared to mel scale cepstral coefficients (MELCEP) in the presence of car noise. Subband analysis based parameters are observed to be more robust than the commonly employed MELCEP representations.

Course
Other identifiers
Book Title
Keywords
Acoustic noise, Computer simulation, Feature extraction, Markov processes, Mathematical models, Numerical analysis, Polynomials, Speech analysis, Vector quantization, Parameter estimation, Pattern recognition systems, Performance, Cepstral coefficient, Line spectral frequency, Linear prediction analysis, Mel scale cepstral coefficient, Speech signal, Subband analysis, Car noise, Hidden Markov model, Linear predictive coding, Mel scale cepstral coefficients, Speech recognition system, Speech recognition
Citation
Published Version (Please cite this version)