Engineering Notes 55
Created by admin on Sat, 31/12/2011 - 10:40
Sub Topic:
Sub-Lexical Modelling
Upload File:
Department:
Chapter Name:
Natural Language Processing
Description:
The finite state transducer (FST) approach [1] has been widely used recently as an effective and flexible framework for speech systems. In this framework, a speech recognizer is represented as the composition of a series of FSTs combining various knowledge sources across sub-lexical and high-level linguistic layers.
Add new comment