Feature extraction based on bio-inspired model for robust emotion recognition (IF 1.271)

ALBORNOZ, E.M.; RUFINER, H.L.; MILONE, D.H.

SOFT COMPUTING - (Print)

SPRINGER

Lugar: Berlin; Año: 2017 vol. 21 p. 5145 - 5158

1472-7643

Emotional state identification is an important issue to achieve more natural speech interactivesystems. Ideally, these systems should also be able towork in real environments in which generally exist somekind of noise. Several bio-inspired representations havebeen applied to artificial systems for speech processing under noise conditions. In this work, an auditory signal representation is used to obtain a novel bio-inspired setof features for emotional speech signals. These characteristics, together with other spectral and prosodic features, are used for emotion recognition under noise conditions. Neural models were trained as classifiers and results were compared to the well-known mel-frequency cepstral coefficients. Results show that using the proposed representations, it is possible to significantly improve the robustness of an emotion recognition system. The results were also validated in a speaker independent scheme and with two emotional speech corpora.