Hierarchical search for large vocabulary conversational speech recognition

Hierarchical search for large vocabulary conversational speech recognition (1999)

Cached

Download Links

[www.ece.msstate.edu]

by Neeraj Deshmukh , Aravind Ganapathiraju , Joseph Picone

Venue:	IEEE Signal Processing Magazine
Citations:	15 - 5 self

Versions

Version History

Metadata Version 0

Datum	Value	Source
TITLE	HIERARCHICAL SEARCH FOR LARGE VOCABULARY CONVERSATIONAL SPEECH RECOGNITION 1	SVM HeaderParse 0.2
AUTHOR NAME	Neeraj Deshmukh	SVM HeaderParse 0.2
AUTHOR AFFIL	Institute for Signal and Information Processing (ISIP); Department of Electrical and Computer Engineering	SVM HeaderParse 0.2
AUTHOR ADDR	Mississippi State University, Mississippi State, MS 39762	SVM HeaderParse 0.2
AUTHOR NAME	Aravind Ganapathiraju	SVM HeaderParse 0.2
AUTHOR AFFIL	Institute for Signal and Information Processing (ISIP); Department of Electrical and Computer Engineering	SVM HeaderParse 0.2
AUTHOR ADDR	Mississippi State University, Mississippi State, MS 39762	SVM HeaderParse 0.2
AUTHOR NAME	Joseph Picone	SVM HeaderParse 0.2
AUTHOR AFFIL	Institute for Signal and Information Processing (ISIP); Department of Electrical and Computer Engineering	SVM HeaderParse 0.2
AUTHOR ADDR	Mississippi State University, Mississippi State, MS 39762	SVM HeaderParse 0.2
ABSTRACT	ABSTRACT 2 Speaker-independent speech recognition technology has made significant progress from the days of isolated word recognition. Today, state-of-the-art systems are capable of performing large vocabulary continuous speech recognition (LVCSR) on audio streams derived from complex information sources such as broadcast news and two-way telephone dialogs. A significant contribution to this advancement in technology is the development of search techniques that find suboptimal but accurate solutions in problems involving large search spaces and extremely complex statistical models. Moreover, these search strategies are capable of dynamically integrating information from a number of diverse knowledge sources to determine the correct word hypothesis, and limit the scope of the search by using a hierarchical search strategy. We refer to this problem as the decoding or search problem. This paper describes the complexity associated with decoding using hierarchical representations for linguistic and acoustic knowledge sources. An extensible object-oriented decoder available in the public domain, that leverages current state-of-the-art technology is described to illustrate these concepts. This decoder supports efficient handling of acoustic models for cross-word contextdependent phones, multiple pronunciations of words using lexical trees, and rescoring of word graphs based on N-gram language models in a single pass. It employs a state-of-the-art Viterbistyle dynamic programming algorithm, and is equipped with several heuristic pruning criteria to minimize the consumption of computational resources while maintaining good accuracy.	SVM HeaderParse 0.2
CITATIONS	69 found	ParsCit 1.0