Speech emotion recognition based on wavelet packet coefficient model
ISCSLP, pp. 478-482, 2014.
frequency resolutionmel-frequency cepstral coefficientssignal representationshort-time analysisgerman languageMore(16+)
Conventional features have achieved good performance in speech emotion recognition. However, these features are based on short-time analysis without considering the non-stationary properties. In this paper we focus on wavelet packet techniques, which can provide an improved signal representation with a tradeoff between time and frequency ...More
Full Text (Upload PDF)
PPT (Upload PPT)