Analyzing And Improving Statistical Language Models For Speech Recognition

Analyzing And Improving Statistical Language Models For Speech Recognition (1994)

by Jörg Ueberla

Citations:

3 - 0 self

User correction supplied by mph

Datum	Value	Source
TITLE	Analyzing And Improving Statistical Language Models For Speech Recognition	user correction - Legacy Corrections
AUTHOR NAME	Jörg Ueberla	user correction
AUTHOR AFFIL	Simon Fraser University	user correction
AUTHOR ADDR		user correction
ABSTRACT	A speech recognizer is a device that translates speech into text. Many current speech recognizers contain two components, an acoustic model and a statistical language model. The acoustic model indicates how likely it is that a certain word corresponds to a part of the acoustic signal (e.g. the speech). The statistical language model indicates how likely it is that a certain word will be spoken next, given the words recognized so far. Even though the acoustic model might for example not be able to decide between the acoustically similar words "peach" and "teach", the statistical language model can indicate that the word "peach" is more likely if the previously recognized words are "He ate the". Current speech recognizers perform well on constrained tasks, but the goal of continuous, speaker independent speech recognition in potentially noisy environments with a very large vocabulary has not been reached so far. How can statistical language models be improved so that more complex tasks c...	user correction - Legacy Corrections
YEAR	1994	user correction - Legacy Corrections
CITATIONS	158 found	ParsCit 1.0