14thAnnual Conference of the International Speech Communication Association

Lyon, France
August 25-29, 2013

Affect Recognition in Real-Life Acoustic Conditions — A New Perspective on Feature Selection

Florian Eyben, Felix Weninger, Björn Schuller

audEERING UG, Germany

Automatic emotion recognition and computational paralinguistics have matured to some robustness under controlled laboratory settings, however, the accuracies are degraded in real-life conditions such as the presence of noise and reverberation. In this paper we take a look at the relevance of acoustic features for expression of valence, arousal, and interest conveyed by a speaker's voice. Experiments are conducted on the GEMEP and TUM AVIC databases. To simulate realistically degraded conditions the audio is corrupted with real room impulse responses and real-life noise recordings. Features well correlated with the target (emotion) over a wide range of acoustic conditions are analysed and an interpretation is given. Classification results in matched and mismatched settings with multi-condition training are provided to validate the benefit of the feature selection method. Our proposed way of selecting features over a range of noise types considerably boosts the generalisation ability of the classifiers.

Full Paper

Bibliographic reference.  Eyben, Florian / Weninger, Felix / Schuller, Björn (2013): "Affect recognition in real-life acoustic conditions — a new perspective on feature selection", In INTERSPEECH-2013, 2044-2048.