Speech Recognition using Neural Networks

Speech Recognition using Neural Networks (1995)

by Joe Tebelskis

Citations:

21 - 0 self

User correction supplied by mph

Datum	Value	Source
TITLE	Speech Recognition using Neural Networks	user correction - Legacy Corrections
AUTHOR NAME	Joe Tebelskis	user correction
AUTHOR AFFIL	School of Computer Science; Carnegie Mellon University	user correction
AUTHOR ADDR	Pittsburgh, Pennsylvania 15213-3890	user correction
ABSTRACT	This thesis examines how artificial neural networks can benefit a large vocabulary, speaker independent, continuous speech recognition system. Currently, most speech recognition systems are based on hidden Markov models (HMMs), a statistical framework that supports both acoustic and temporal modeling. Despite their state-of-the-art performance, HMMs make a number of suboptimal modeling assumptions that limit their potential effectiveness. Neural networks avoid many of these assumptions, while they can also learn complex functions, generalize effectively, tolerate noise, and support parallelism. While neural networks can readily be applied to acoustic modeling, it is not yet clear how they can be used for temporal modeling. Therefore, we explore a class of systems called NN-HMM hybrids, in which neural networks perform acoustic modeling, and HMMs perform temporal modeling. We argue that a NN-HMM hybrid has several theoretical advantages over a pure HMM system, including better acoustic ...	user correction - Legacy Corrections
YEAR	1995	INFERENCE
VENUE TYPE	TECHREPORT	INFERENCE
TECH	Ph. D. dissertation	INFERENCE
CITATIONS	140 found	ParsCit 1.0