Automatic Prosodic and Syntactic Analysis from Speech in Cognitive Infocommunication

Speech prosody and speech syntax are closely related, and this correspondence - syntax to prosody mapping - is exploited in text-to-speech infocommunication applications. However, in automatic speech recognition and understanding based inter-cognitive infocommunication, the use of prosody to syntax mapping is mostly restricted to minimal pair disambiguation purposes, although a partial recovery of the syntactic structure can be feasible based on speech prosody. This paper presents an experiment for the automatic analysis of the prosodic and syntactic structure of speech based on automatic alignment of prosodic units - so called phonological phrases. Results show that a basic skeleton of the underlying syntactic structure and also some layering (hierarchical) information can be reconstructed based on speech prosody.