Some relations among stochastic finite state networks used in automatic speech recognition

Author

Casacuberta, Francisco

Author_Institution

Dept. of Sistemas Inf. y Comput., Universidad Politecnica de Valencia, Spain

Volume

12

Issue

7

fYear

1990

fDate

7/1/1990 12:00:00 AM

Firstpage

691

Lastpage

695

Abstract

In the literature on automatic speech recognition, the popular hidden Markov models (HMMs), left-to-right hidden Markov models (LRHMMs), Markov source models (MSMs), and stochastic regular grammars (SRGs) are often proposed as equivalent models. However, no formal relations seem to have been established among these models to date. A study of these relations within the framework of formal language theory is presented. The main conclusion is that not all of these models are equivalent, except certain types of hidden Markov models with observation probability distribution in the transitions, and stochastic regular grammar

Keywords

Markov processes; formal languages; grammars; speech recognition; stochastic processes; automatic speech recognition; formal language theory; hidden Markov models; observation probability distribution; stochastic finite state networks; stochastic regular grammar; Automata; Automatic speech recognition; Formal languages; Hidden Markov models; Information theory; Intelligent networks; Natural languages; Probability distribution; Production; Speech recognition; Stochastic processes;

fLanguage

English

Journal_Title

Pattern Analysis and Machine Intelligence, IEEE Transactions on

Publisher

ieee

ISSN

0162-8828

Type

jour

DOI

10.1109/34.56212

Filename

56212