A Prosodic/Syntactic Model for Integrating Prosody in a Continuous Speech Recognition System

This paper presents a statistical model, which associates syntactic rules with prosodic cues in order to help a continuous speech recognition system produce sentence hypotheses. The system consists of the sequential coupling of a standard speech recognizer and a syntactic parser working on lattices of hypotheses by means of a Stochastic Context -Free Grammar (SCFG). The prosodic/syntactic model describes relations between the rules of the SCFG and "prosodic vectors" extracted from the signal. The parser has been modified to cope with such prosodically enhanced rules. The output of the system is a list of hypotheses scored using the merged syntactic/prosodic model.