Date: Wed, 1 Sep 1999 00:20:43 -0500 (CDT)
X-Authentication-Warning: isip18.isip.msstate.edu: zhao set sender to zhao@isip.msstate.edu using -f
From: Jie Zhao <zhao@ISIP.MsState.EDU>
To: picone@ISIP00.ISIP.MsState.Edu
Subject: abstract of ece7000 talk 1
Reply-to: zhao@ISIP.MsState.EDU
Content-Type: text
Content-Length: 1229



Title: Introduction to Finite State Machines

Finite state machine (FSM) is a network which has finite number 
of states. Given an input, the machine can transfer from
one state to another and generate an output. In speech recognition, 
each acoustic model (usually the Hidden Markov model) and each language 
models is a small FSM. All these small FSMs comprise a big and 
complicated FSM or network, that is the search space in decoding. 
The aim of decoding is to find the best path among this big network. 
Therefore understanding how FSMs operate is fundamental to the research
on speech recognition.   

In this talk, I will introduce the fundamental theories about FSM 
and its applications in speech recognition :


1. Types of FSMs : deterministic and nondeterministic

2. Operations on FSMs.

   Union (sum), Concatenation, Epsilon removal,
   Difference, Composition, Determinization, Best path, etc.
   And along with AT&T FSM tutorial, I'll talk about the algorithms
   to do these operations.

3. FSMs in speech recognition

   + Hidden Markov Models
   + N-gram language model




---------------------------------------------------------------
I'll give the abstract of the second talk a short later.




-zhao