Wavelet based analysis of speech under stress
- 22 November 2002
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
Abstract
Stress and its effects in speech signals have been studied by many researchers. A number of studies have been attempted to determine reliable acoustic indicators of stress using such speech production features as fundamental frequency (F0), intensity, spectral tilt, the distribution of spectral energy and others. The findings indicate that more work is necessary to propose a general solution. The goal of this study is to propose a new set of speech features based on dyadic wavelet transform (DyWT) coefficients as potential stress sensitive parameters. The parameters' ability to capture different stress types is evaluated on the basis of separability distance measure between parameters of each stress class for four stress conditions: neutral, loud, question and angry. After an extensive number of scatter distributions were considered a number of clear trends emerged that confirmed that the new speech parameters are well suited for stress classification.Keywords
This publication has 9 references indexed in Scilit:
- Robust classification of speech based on the dyadic wavelet transform with application to CELP codingPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2002
- Feature analysis and neural network-based classification of speech under stressIEEE Transactions on Speech and Audio Processing, 1996
- Stress independent robust HMM speech recognition using neural network stress classificationPublished by International Speech Communication Association ,1995
- Robust speech recognition training via duration and spectral-based stress token generationIEEE Transactions on Speech and Audio Processing, 1995
- Nonlinear analysis and classification of speech under stressed conditionsThe Journal of the Acoustical Society of America, 1994
- Low bit rate transparent audio compression using adapted waveletsIEEE Transactions on Signal Processing, 1993
- Characterization of signals from multiscale edgesPublished by Institute of Electrical and Electronics Engineers (IEEE) ,1992
- Application of the wavelet transform for pitch detection of speech signalsIEEE Transactions on Information Theory, 1992
- Wavelets and signal processingIEEE Signal Processing Magazine, 1991