METHOD OF PATTERN RECOGNITION USING NOISE REDUCTION UNCERTAINTY

Patent №

US 7,103,540

Granted

2006-09-05

Filed 2002

Owner

MICROSOFT CORPORATION

AI components

6

ml · nlp · vision · speech · evo · hardware

Assignment

Recorded

Dataset

AIPD

2023_r1 edition

Application

10152127

A method and apparatus are provided for using the uncertainty of a noise-removal process during pattern recognition. In particular, noise is removed from a representation of a portion of a noisy signal to produce a representation of a cleaned signal. In the meantime, an uncertainty associated with the noise removal is computed and is used with the representation of the cleaned signal to modify a probability for a phonetic state in the recognition system. In particular embodiments, the uncertainty is used to modify a probability distribution, by increasing the variance in each Gaussian distribution by the amount equal to the estimated variance of the cleaned signal, which is used in decoding the phonetic state sequence in a pattern recognition task.

AI classification

Machine learning1.00
Speech1.00
AI hardware1.00
Natural language0.95
Evolutionary computation0.84
Vision0.81
Planning0.20
Knowledge representation0.18

Ownership

MICROSOFT CORPORATION

assignment · 129260541

Assignors

DROPPO, JAMES G., ACERO, ALEJANDRO, DENG, LI

On an employer assignment, the assignors are typically the inventors.

© 2026 NYSGPT2525 LLC