Speech Recognition System Design Based on Automatically Derived Units

Speech Recognition System Design Based on Automatically Derived Units (1999)

by Michiel A. Bacchiani

Citations:

10 - 0 self

User correction supplied by mph

Datum	Value	Source
TITLE	Speech Recognition System Design Based on Automatically Derived Units	user correction - Legacy Corrections
AUTHOR NAME	Michiel A. Bacchiani	user correction
ABSTRACT	In most speech recognition systems today, acoustic modeling and lexical modeling are viewed as separable problems. Currently the most popular approach is to manually define canonical word pronunciations in terms of phonetic units and let the acoustic models capture differences between actual spoken and canonical pronunciations implicitly with Gaussian mixture models. As a result, these models can be very broad, particularly for casual spontaneous speech. An alternative approach, explored in this thesis, is to learn a unit inventory and pronunciation dictionary from training data using a maximum likelihood objective function. In particular,	user correction
YEAR	1999	SVM HeaderParse 0.1
CITATIONS	75 found	ParsCit 1.0