Abstract | In the last decade there has been an increasing tendency to incorporate
language engineering strategies into speech technology. This technique
combines linguistic and mathematical information in different applications:
machine ...
In the last decade there has been an increasing tendency to incorporate
language engineering strategies into speech technology. This technique
combines linguistic and mathematical information in different applications:
machine translation, natural language processing, speech synthesis and
automatic speech recognition (ASR). In the field of speech synthesis, this
hybrid approach (linguistic and mathematical/statistical) has led to the
design of efficient models for reproducing the acoustic features of natural
language. However, the incorporation of language engineering strategies
into ASR is only beginning. In this paper, we present a theoretical
framework for the integration of linguistic information into an ASR system.
The objective is to design a model which can detect the suprasegmental
features of the speech input, mainly those related to the fundamental
frequency (F0) that can clarify the functionality of pauses, intonation
contour, and interruptions. This specification model has been designed in
the framework of a dialogue system
|