Universidad de Costa Rica

Assessing stress in mexican spanish from emotion speech signals


Colaboradores:
Ing. Marvin Coto Jiménez, PhD.
Autores:
FM Martinez-Licona and J Goddard and AE Martínez-Licona1M Coto Jiménez
Revista:
Proc. 8th International Workshop on Models and Analysis of Vocal Emissions for Biomedical Applications, MAVEBA
Editor:
N/A
URL:
https://www.researchgate.net/profile/Daniela_Lenti_Boero/publication/299445971_Premature_infants'_cry_maintains_abnormalities_at_term_a_sonospectrographic_study/links/56f812c808ae81582bf398f0/Premature-infants-cry-maintains-abnormalities-at-term-a-sonospectrographic-study.pdf#page=253

Resumen:

Stress is considered a very serious condition that is a consequence of several alterations. In Mexico it affects about half of the adult population and is considered as the most important issue that young working people and women have to deal. The stressful condition is a complex process that can be partially evaluated through the speech since they can be obtained non-invasively and the signals can be analyzed form acoustic features as well as prosodic and other non-linguistic elements. In this paper, an evaluation of stress from an analysis of Mexican Spanish emotional speech signals is presented. Anger, disgust, fear and a normal state are obtained from a two speakers database and pitch, jitter and shimmer features were extracted. Results show that anger and fear are the emotions that can present useful information for the stress evaluation.

© 2020 Escuela de Ingeniería Eléctrica, Universidad de Costa Rica.