Perception of Alcoholic Intoxication in Speech

The ALC sub-challenge of the Interspeech Speaker State Challenge (ISSC) aims at the automatic classification of speech signals into intoxicated and sober speech. In this context we conducted a perception experiment on data derived from the same corpus to analyze the human performance on the same task. The results show that human still outperform comparable baseline results of ISSC. Female and male listeners perform on the same level, but there is strong evidence that intoxication in female voices is easier to be recognized than in male voices. Prosodic features contribute to the decision of human listeners but seem not to be dominant. In analogy to Doddington’s zoo of speaker verification we find some evidence for the existence of lambs and goats but no wolves.