Imaxe de Portada

Nonlinear feature based classification of speech under stress.

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 spee...

Descrición completa

Detalles Bibliográficos
Publicado en:IEEE Transactions on speech and audio processing 9, 3 (2001).
Autor Principal: Zhou, G.
Formato: Artigo
Idioma:inglés
Subjects:
TEO autocorrelation envelope area.
TEO-decomposed FM variation.
Acoustic variables.
Actual stressed speech.
Critical band.
Emotion.
Linear speech production theory.
Mel-frequency cepstrum coefficients.
Nonlinear Teager energy operator.
Nonlinear airflow structure.
Nonlinear feature based speech classification.
Normalized TEO autocorrelation envelope area.
Simulated stressed speech.
Speech production.
Speech recognition systems.
Stress classification rates.
Text-dependent models.
Text-independent models.