AI tools for speech analysis applied to the Romanian language
Horia-Nicolai Teodorescu · 2010
I present recent advances in the characterization of spoken Romanian language and tools used for perceptual and statistical analysis. Problems overviewed in the plenary talk are the analysis, description and recognition of emotions in voice, the comparison of emotional speech characteristics in different European languages, interaction of grammar and speech in specific grammatical constructions, phonetic statistics for the Romanian language, and pathologies' effects on speech. I overview the principles of the computational tools developed and results of speech analysis, with an emphasis on spoken language statistics and emotional analysis and recognition in speech. In this paper, aimed for the conference proceedings, I describe only a tool for speech file analysis and for data mining in such files.