User Settings
Article10.21437/eurospeech.1999-281x

Speed improvement of the time-asynchronous acoustic fast match

Miroslav Novák,Michael Picheny-1999-09-05
2

TL;DRAbstract

This paper describes an algorithm for improvement of the speed of a time-asynchronous fast match, which is a part of a stack-search based recognition system. This fast match uses a phonetic tree to represent the entire vocabulary of the recognizer. Evaluation of the tree (in a depthrst manner), can be done much more e ciently using the fact that under certain conditions, the results of branch evaluations can be used to approximate the scores of other branches of the tree.

Chat with Paper

AI Agents for this Paper

This paper describes an algorithm for improvement of the speed of a time-asynchronous fast match, which is a part of a stack-search based recognition system. This fast match uses a phonetic tree to represent the entire vocabulary of the recognizer. Evaluation of the tree (in a depthrst manner), can be done much more e ciently using the fact that under certain conditions, the results of branch evaluations can be used to approximate the scores of other branches of the tree.

Keywords

Asynchronous communicationComputer scienceTree (set theory)Stack (abstract data type)VocabularySpeech recognitionSpeedupTrie

Chat

Click to start Chat