Abstract
This paper presents the results of research on the effect of variation of acoustic features of voice quality in verbal expression of emotions. The research was based on software MDVP (Multidimensional Voice Program) and measuring on the set of recorded spoken sentences from the Serbian emotional database GEES (Voice Expression of Emotions and Attitudes). The analysis entailed comparison of neutral and emotional speech (joy and anger). The results showed the superiority of the analysis of accented syllables compared to the analysis of sentences. From a preliminary set of selected acoustic features, the following features were highlighted: Jitt, RAP and NHR. Measured variations of these parameters proved to be distinct and precise discriminators of strong emotions such as joy and anger.
Sign-in/Register to access full text options 
Free) 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
