Please use this identifier to cite or link to this item:
Title: Stress classification using subband based features
Authors: Nwe, T.L. 
Foo, S.W.
De Silva, L.C. 
Keywords: Log Frequency Power Coefficients
Nonlinear frequency domain LFPC feature
Nonlinear time domain LFPC features
Stress classification
Issue Date: 2003
Citation: Nwe, T.L.,Foo, S.W.,De Silva, L.C. (2003). Stress classification using subband based features. IEICE Transactions on Information and Systems E86-D (3) : 565-573. ScholarBank@NUS Repository.
Abstract: On research to determine reliable acoustic indicators for the type of stress present in speech, the majority of systems have concentrated on the statistics extracted from pitch contour, energy contour, wavelet based subband features and Teager-Energy-Operator (TEO) based feature parameters. These systems work mostly on pair-wise distinction between stress and neutral speech. Their performance decreases substantially when tested in multi-style detection among many stress categories. In this paper, a novel system is proposed using linear short time Log Frequency Power Coefficients (LFPC) and TEO based nonlinear LFPC features in both time and frequency domain. Five-state Hidden Markov Model (HMM) with continuous Gaussian mixture distribution is used. The stress classification ability of the system is tested using data from the SUSAS (Speech Under Simulated and Actual Stress) database to categorize five stress conditions individually. It is found that the performance of linear acoustic features LFPC is better than that of nonlinear TEO based LFPC feature parameters. Results show that with linear acoustic feature LFPC, average accuracy of 84% and the best accuracy of 95% can be achieved in the classification of the five categories. Results of test of the system under different signal-to-noise conditions show that the performance of the system does not degrade drastically with increase in noise. It is also observed that classification using nonlinear frequency domain LFPC features gives relatively higher accuracy than that using nonlinear time domain LFPC features.
Source Title: IEICE Transactions on Information and Systems
ISSN: 09168532
Appears in Collections:Staff Publications

Show full item record
Files in This Item:
There are no files associated with this item.

Page view(s)

checked on Dec 2, 2021

Google ScholarTM


Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.