The INTERSPEECH 2018 Self-Assessed Affect Challenge consists in the prediction of the affective state of mind from speech. Experiments were conducted on the Ulm State-of-Mind in Speech database (USoMS) where subjects self-report their affective state. Dimensional representation of emotion (valence) is used for labeling. We have investigated cues related to the perception of the emotional valence according to three main relevant linguistic levels: phonetics, lexical and prosodic. For this purpose we studied: the degree-of-articulation, the voice quality, an affect lexicon and the expressive prosodic contours. For the phonetics level, a set of gender-dependent audio-features was computed on vowel analysis (voice quality and speech articulation measurements). At the lexical level, an affect lexicon was extracted from the automatic transcription of the USoMS database. This lexicon has been assessed for the Challenge task comparatively to a reference polarity lexicon. In order to detect expressive prosody, N-gram models of the prosodic contours were computed from an intonation labeling system. At last, an emotional valence classifier was designed combining ComParE and eGeMAPS feature sets with other phonetic, prosodic and lexical features. Experiments have shown an improvement of 2.4% on the Test set, compared to the baseline performance of the Challenge.
Cite as: Montacié, C., Caraty, M.-J. (2018) Vocalic, Lexical and Prosodic Cues for the INTERSPEECH 2018 Self-Assessed Affect Challenge. Proc. Interspeech 2018, 541-545, doi: 10.21437/Interspeech.2018-1331
@inproceedings{montacie18_interspeech,
author={Claude Montacié and Marie-José Caraty},
title={{Vocalic, Lexical and Prosodic Cues for the INTERSPEECH 2018 Self-Assessed Affect Challenge}},
year=2018,
booktitle={Proc. Interspeech 2018},
pages={541--545},
doi={10.21437/Interspeech.2018-1331}
}