Emotional aspects of intrinsic speech variabilities in automatic speech recognition
Miloš Cerňak · 2006
We analyze two German databases: the OLLO database [1] designed for doing speech recognition experiments on speech variabilities, and the Berlin emotional database [2] designed for the analysis and synthesis of emotional speech. The paper tries to nd a relation between intrinsic speech variabilities and the emotions. Moreover, we study this relation from the point of view of speech recognition. Acoustical analysis is performed on both databases, using Normalized Amplitude Quotient and F0 parameterization of ve analyzed vowels [a], [e], [i], [o], and [u], merging their long and short variants. Euclidean distance between the feature vectors of both databases is used for nding the relation, named as emotional aspect of speech variabilities. The speech recognition experiments on the OLLO database show that found emotional aspects have also a discrimination power.