Pre-Grant Publication Number: 20100262423
Filing Date: April 13, 2009Priority Date: April 13, 2008
Inventors: Qiang Huo, Jun Du
Assignee(s): Microsoft Corporation
Current U.S. Classification: 704, 704/233000, 704/E15004
View Prior Art for Claim 00001
In a computing environment, a method comprising, receiving feature vectors for an unknown utterance, compensating for additive noises or convolutional distortions, or both additive noise and convolutional distortions, including by using a high-order vector Taylor series approximation of a model of distortions to provide compensated feature vectors to a speech recognizer.
#636The application of Taylor series
Applies to Claims 1,10,2,3,4,5,6,7,8,9
Submitted by: Mehmet YilmazLast updated: over 2 years ago
Title OVERCOMING THE VECTOR TAYLOR SERIES APPROXIMATION IN SPEECH FEATURE ENHANCEMENT — A PARTICLE FILTER
ISBN
Description
It appears the use of vector taylor series approximation in speech has already existed
1 thumb up 0 thumbs down
Annotations(0)
Submitted by: Christopher IlardiLast updated: over 2 years ago
Title
ISBN 0-7803-3192-3
Description
An analytical approach to environment compensation for speech recognition. Uses the Vector Taylor Series expansion to characterize the effects on speech statistics of unknown noise.
1 thumb up 0 thumbs down
Annotations(0)
Submitted by: Christopher IlardiLast updated: over 2 years ago
Title IEEE SIGNAL PROCESSING LETTERS
ISBN
Description
From the abstract:The statistical linear approximation (SLA) method is proposed as a novel way to approximate a nonlinear function by a linearized model. In the proposed method, an optimization criterion for approximation is defined in terms of statistical expectation. The SLA is applied to environment compensation where the speech contamination rule appears as a highly nonlinear function of the relevant variables.
1 thumb up 0 thumbs down
Annotations(0)