Patent №
US 8,346,554
Granted
2013-01-01
Filed 2010
Owner
—
Lab
—
AI components
4
ml · nlp · speech · hardware
Assignment
None on record
Dataset
AIPD
2023_r1 edition
Application
12882292
A method for automatic speech recognition includes determining for an input signal a plurality scores representative of certainties that the input signal is associated with corresponding states of a speech recognition model, using the speech recognition model and the determined scores to compute an average signal, computing a difference value representative of a difference between the input signal and the average signal, and processing the input signal in accordance with the difference value.