OpenVokaturi 1.0 launched
14 April 2016
Given speech that comes in as a sampled sound, the Vokaturi software computes five acoustic features: pitAve, pitSlo, intAve, intSlo, spcSlo. From these features, the software computes probabilities for the five main emotions: neutrality, happiness, sadness, anger, fear.
The method is linear discriminant analysis,