Abstract
Emotions in continuous speech were analyzed using inverse filtering and a recently developed glottal flow parameter, the normalized amplitude quotient (NAQ). Simulated emotion portrayals were produced by 9 professional stage actors. Segments of the vowel /a:/ were separated from continuous speech. The segments were inverse filtered and parametrized using NAQ. Statistical analyses showed significant differences between most studied emotions. Results also showed clear gender differences. Inverse filtering together with NAQ was shown to be a suitable method for analysis of emotional content in continuous speech.
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have