Method of noise reduction using correction and scaling vectors with partitioning of the acoustic space in the domain of noisy speech

• US 20050149325A1
• Filed: 02/16/2005
• Published: 07/07/2005
• Est. Priority Date: 10/16/2000
• Status: Active Grant

• Current Assignee: Microsoft Technology Licensing LLC (Microsoft Corporation)
• Original Assignee: Microsoft Corporation
• Inventors: Deng, Li, Acero, Alejandro, Huang, Xuedong
• Granted Patent: US 7,254,536 B2
• Time in Patent Office: Days
• US Class Current: 704/226
• CPC Class Codes: G10L 21/0208 Noise filtering

Abstract

A method and apparatus are provided for reducing noise in a training signal and/or test signal. The noise reduction technique uses a stereo signal formed of two channel signals, each channel containing the same pattern signal. One of the channel signals is “clean” and the other includes additive noise. Using feature vectors from these channel signals, a collection of noise correction and scaling vectors is determined. When a feature vector of a noisy pattern signal is later received, it is multiplied by the best scaling vector for that feature vector and the best correction vector is added to the product to produce a noise reduced feature vector. Under one embodiment, the best scaling and correction vectors are identified by choosing an optimal mixture component for the noisy feature vector. The optimal mixture component being selected based on a distribution of noisy channel feature vectors associated with each mixture component.

Claims

1. A method of noise reduction for reducing noise in a noisy input signal, the method comprising:

grouping noisy channel feature vectors and clean channel feature vectors into a plurality of mixture components;

fitting a function applied to noisy channel feature vectors associated with a mixture component to only those clean channel feature vectors that are associated with the same mixture component to determine at least one correction vector and at least one scaling vector;

multiplying the scaling vector by a noisy input feature vector to produce a scaled feature vector; and

adding a correction vector to the scaled feature vector to form a clean input feature vector.

2. The method of claim 1 wherein determining a correction vector comprises:

grouping the noisy channel feature vectors into at least one mixture component;

determining a distribution value that is indicative of the distribution of the noisy channel feature vectors in at least one mixture component; and

using the distribution value for a mixture component to determine the correction vector and the scaling vector for that mixture component.

3. The method of claim 2 wherein using the distribution value to determine a correction vector and a scaling vector for a mixture component comprises:

determining, for each noisy channel feature vector, at least one conditional mixture probability, the conditional mixture probability representing the probability of the mixture component given the noisy channel feature vector, the conditional mixture probability based in part on a distribution value for the mixture component; and

applying the conditional mixture probability in a linear least squares calculation.

4. The method of claim 3 wherein determining a conditional mixture probability comprises:

determining a conditional feature vector probability that represents the probability of a noisy channel feature vector given the mixture component, the probability based on the distribution value for the mixture;

multiplying the conditional feature vector probability by the unconditional probability of the mixture component to produce a probability product; and

dividing the probability product by the sum of the probability products generated for all mixture components for the noisy channel feature vector.

5. The method of claim 4 wherein determining a conditional feature vector probability comprises determining the probability from a normal distribution formed from the distribution value for a mixture component.

6. The method of claim 5 wherein determining a distribution value comprises determining a mean vector and determining a standard deviation vector.

7. The method of claim 1 wherein multiplying the scaling vector by a noisy input feature vector comprises:

identifying a mixture component for the noisy input feature vector; and

multiplying the noisy input feature vector by a scaling vector associated with the mixture component.

8. The method of claim 7 wherein adding a correction vector comprises adding a correction vector associated with the mixture component to the scaled feature vector.

9. The method of claim 8 wherein identifying a mixture component comprises identifying the most likely mixture component for the noisy input feature vector.

10. The method of claim 9 wherein identifying the most likely mixture component comprises:

grouping the noisy channel feature vectors into at least one mixture component;

determining a distribution value that is indicative of the distribution of the noisy channel feature vectors in at least one mixture component;

for each mixture component, determining a probability of the noisy input feature vector given the mixture component based on a normal distribution formed from the distribution value for that mixture component; and

selecting the mixture component that provides the highest probability as the most likely mixture component.

11. A method of reducing noise in a noisy signal, the method comprising:

identifying a single mixture component for a noisy feature vector representing a part of the noisy signal;

retrieving a correction vector and a scaling vector associated with the identified mixture component;

multiplying the noisy feature vector by the scaling vector to form a scaled feature vector; and

adding the correction vector to the scaled feature vector to form a clean feature vector representing a part of a clean signal.

12. The method of claim 11 wherein identifying a mixture component comprises identifying a most likely mixture component for a noisy feature vector.

13. A method of generating correction values for removing noise from an input signal, the method comprising:

accessing a set of noisy channel vectors representing a noisy channel signal;

accessing a set of clean channel vectors representing a clean channel signal;

grouping the noisy channel vectors into a plurality of mixture components based on the noisy channel vectors; and

determining a correction value for a mixture component.

14. The method of claim 13 wherein determining a correction value comprises fitting a function based on noisy channel vectors to clean channel vectors.

15. The method of claim 14 wherein fitting a function comprises performing a linear least squares calculation.

16. The method of claim 13 wherein determining a correction value comprises determining an additive correction value and a scaling correction value.