Nonlinear feature based classification of speech under stress

• Published in: IEEE transactions on speech and audio processing Vol. 9; no. 3; pp. 201 - 216
• Main Authors: Zhou, G., Hansen, J.H.L., Kaiser, J.F.
• Format: Journal Article
• Language: English
• Published: New York, NY IEEE 01.03.2001; Institute of Electrical and Electronics Engineers
• Subjects: Acoustic noise; Applied sciences; Artificial intelligence; Autocorrelation; Classification; Computer science; control theory; systems; Envelopes; Exact sciences and technology; Information, signal and communications theory; Laboratories; Mathematical models; Multitasking; Nonlinearity; Robustness; Signal processing; Speech; Speech analysis; Speech and sound recognition and synthesis. Linguistics; Speech processing; Speech recognition; Stress; Stresses; Telecommunications and information theory; Working environment noise; Classification scheme; Stress analysis; Speech analysis; Speech recognition; Theoretical study; Non linear structure; Speech synthesis; Speech processing; Human factor
• ISSN: 1063-6676; 1558-2353
• DOI: 10.1109/89.905995

Studies have shown that variability introduced by stress or emotion can severely reduce speech recognition accuracy. Techniques for detecting or assessing the presence of stress could help improve the robustness of speech recognition systems. Although some acoustic variables derived from linear speech production theory have been investigated as indicators of stress, they are not always consistent. Three new features derived from the nonlinear Teager (1980) energy operator (TEO) are investigated for stress classification. It is believed that the TEO based features are better able to reflect the nonlinear airflow structure of speech production under adverse stressful conditions. The features proposed include TEO-decomposed FM variation (TEO-FM-Var), normalized TEO autocorrelation envelope area (TEO-Auto-Env), and critical band based TEO autocorrelation envelope area (TEO-CB-Auto-Env). The proposed features are evaluated for the task of stress classification using simulated and actual stressed speech and it is shown that the TEO-CB-Auto-Env feature outperforms traditional pitch and mel-frequency cepstrum coefficients (MFCC) substantially. Performance for TEO based features are maintained in both text-dependent and text-independent models, while performance of traditional features degrades in text-independent models. Overall neutral versus stress classification rates are also shown to be more consistent across different stress styles.