Time Dependent ARMA for Automatic Recognition of Fear-Type Emotions in Speech

Vasquez-Correa JC, Orozco-Arroyave JR, Arias-Londono JD, Vargas-Bonilla JF, Avendano LD, Nöth E (2015)

Publication Status: Published

Publication Type: Conference contribution

Publication year: 2015

Journal

Lecture Notes in Computer Science Springer Verlag

Publisher: Springer-verlag

Book Volume: 9302

Pages Range: 96-104

DOI: 10.1007/978-3-319-24033-6_11

Abstract

The speech signals are non-stationary processes with changes in time and frequency. The structure of a speech signal is also affected by the presence of several paralinguistics phenomena such as emotions, pathologies, cognitive impairments, among others. Non-stationarity can be modeled using several parametric techniques. A novel approach based on time dependent auto-regressive moving average (TARMA) is proposed here to model the non-stationarity of speech signals. The model is tested in the recognition of "fear-type" emotions in speech. The proposed approach is applied to model syllables and unvoiced segments extracted from recordings of the Berlin and enterface05 databases. The results indicate that TARMA models can be used for the automatic recognition of emotions in speech.

Authors with CRIS profile

Elmar Nöth Professur für Informatik (Mustererkennung)

Involved external institutions

University of Patras (UPATRAS) GR Greece (GR) Universidad de Antioquía (UDEA) CO Colombia (CO)

How to cite

APA:

Vasquez-Correa, J.C., Orozco-Arroyave, J.R., Arias-Londono, J.D., Vargas-Bonilla, J.F., Avendano, L.D., & Nöth, E. (2015). Time Dependent ARMA for Automatic Recognition of Fear-Type Emotions in Speech. (pp. 96-104). Springer-verlag.

MLA:

Vasquez-Correa, J. C., et al. "Time Dependent ARMA for Automatic Recognition of Fear-Type Emotions in Speech." Springer-verlag, 2015. 96-104.

BibTeX: Download