Noise reduction using correction vectors based on dynamic aspects of speech and noise normalization

• US 7,181,390 B2
• Filed: 07/26/2005
• Issued: 02/20/2007
• Est. Priority Date: 04/05/2002
• Status: Expired due to Term

• Current Assignee: Microsoft Technology Licensing LLC (Microsoft Corporation)
• Original Assignee: Microsoft Corporation
• Inventors: Deng, Li, Droppo, James G., Acero, Alejandro
• Primary Examiner(s): {hacek over (S)}mits; Talivaldis Ivars
• Assistant Examiner(s): Serrou; Abdelali
• Application Number:
  US11/189,974
• Publication Number:
  US 20050259558A1
• Time in Patent Office: 574 Days
• Field of Search: 704/224, 704226-228, 704/234
• 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 signal. Under one aspect of the invention, a correction vector is selected based on a noisy feature vector that represents a noisy signal. The selected correction vector incorporates dynamic aspects of pattern signals. The selected correction vector is then added to the noisy feature vector to produce a cleaned feature vector. In other aspects of the invention, a noise value is produced from an estimate of the noise in a noisy signal. The noise value is subtracted from a value representing a portion of the noisy signal to produce a noise-normalized value. The noise-normalized value is used to select a correction value that is added to the noise-normalized value to produce a cleaned noise-normalized value. The noise value is then added to the cleaned noise-normalized value to produce a cleaned value representing a portion of a cleaned signal.

Claims

1. A computer-readable medium having computer-executable instructions for reducing noise in a noisy signal through steps comprising:

forming a correction vector based on dynamic aspects of a signal, the correction vector having static coefficients and dynamic coefficients, the dynamic coefficients comprising delta coefficients; and

adding the correction vector to a feature vector representing a portion of the noisy signal to produce a clean feature vector representing a portion of a clean signal.

2. The computer-readable medium of claim 1 wherein forming a correction vector comprises:

converting n frames of the noisy signal into n respective feature vectors; and

using the n feature vectors to select a correction vector.

3. The computer-readable medium of claim 2 wherein using the n feature vectors to select a correction vector comprises:

comparing the set of n feature vectors to distributions of training sets of n feature vectors to find a distribution that best matches the set of n feature vectors; and

selecting a correction vector that is associated with the distribution that best matches the set of n feature vectors.

4. The computer-readable medium of claim 1 wherein forming the correction vector comprises:

selecting a sequence of correction vectors;

applying the sequence of correction vectors to a filter to produce a sequence of filtered correction vectors; and

selecting one of the filtered correction vectors.

5. The computer-readable medium of claim 4 wherein selecting a sequence of correction vectors comprises selecting a sequence of correction vectors having only static coefficients.

6. The computer-readable medium of claim 4 wherein the filter has a transfer function that is based on dynamic aspects of a signal.

7. The computer-readable medium of claim 6 wherein the filter is a time-invariant filter.

8. A method for reducing noise in a noisy signal, the method comprising:

estimating noise in a portion of the noisy signal;

subtracting a feature vector representation of the noise estimate from a feature vector representation of the portion of the noisy signal to produce a noise-normalized value;

using the noise-normalized value to identify a correction vector;

adding the correction vector to the noise-normalized value to produce a noise-normalized clean value; and

adding the feature vector representation of the noise estimate to the noise-normalized clean value to produce a feature vector representation of a portion of a clean signal.

9. The method of claim 8 wherein the feature vector representation is a cepstral domain representation.

10. The method of claim 8 wherein using the noise-normalized value to identify a correction vector comprises:

applying the noise-normalized value to a set of distributions of noise-normalized training values to identify a distribution that best matches the noise-normalized value; and

selecting a correction vector associated with the distribution that best matches the noise-normalized value.

11. A computer-readable medium having computer-executable instructions for reducing noise in a noisy signal through steps comprising:

subtracting a noise value from a noisy signal value derived from the noisy signal to produce a noise-normalized value;

selecting a correction value based on the noise-normalized value;

adding the correction value to the noise-normalized value to produce a cleaned noise-normalized value; and

adding the noise value to the cleaned noise-normalized value to produce a cleaned value.

12. The computer-readable medium of claim 11 further comprising generating the noise value based on an estimate of the noise in the noisy signal.

13. The computer-readable medium of claim 12 wherein the noisy signal value is a feature vector representing a portion of the noisy signal and the noise value is a feature vector representing an estimate of the noise in the portion of the noisy signal.

14. The computer-readable medium of claim 13 wherein the feature vectors are cepstral feature vectors.

15. The computer-readable medium of claim 11 wherein selecting a correction value comprises:

comparing the noise-normalized value to distribution values that describe distributions of training noise-normalized values;

based on the comparison, selecting one of the distributions of training noise-normalized values; and

selecting a correction value associated with the selected distribution.

16. A computer-readable medium having computer-executable instructions for reducing noise in a noisy signal through steps comprising:

forming a correction vector based on dynamic aspects of a signal, the correction vector having static coefficients and dynamic coefficients, the dynamic coefficients comprising acceleration coefficients; and

adding the correction vector to a feature vector representing a portion of the noisy signal to produce a clean feature vector representing a portion of a clean signal.