Skip to main content
EURASIP Journal on Audio, Speech, and Music Processing
Figure 3 | EURASIP Journal on Audio, Speech, and Music Processing

Figure 3

From: Perceptual audio features for emotion detection

Figure 3

Coupled reference set and the perceptual features. An utterance is represented by N perceptual feature vectors each extracted with respect to a reference audio sample. Hence, the perceptual feature vectors reflect the variation of every emotional audio sample from the reference set.

Back to article page