Microphone array signal enhancement using mixture models

• US 7,103,541 B2
• Filed: 06/27/2002
• Issued: 09/05/2006
• Est. Priority Date: 06/27/2002
• Status: Expired due to Fees

• Current Assignee: Microsoft Technology Licensing LLC (Microsoft Corporation)
• Original Assignee: Microsoft Corporation
• Inventors: Deng, Li, Attias, Hagai
• Primary Examiner(s): CHAWAN, VIJAY B
• Application Number:
  US10/183,267
• Publication Number:
  US 20040002858A1
• Time in Patent Office: 1,531 Days
• Field of Search: 704225-228, 704/233, 704/219, 704/256, 381/94.3, 381/94.2, 381/320, 379/290
• US Class Current: 704/226
• CPC Class Codes: G10L 2021/02161 Number of inputs available containing the signal or the noise to be suppressed
• CPC Class Codes: G10L 21/02 Speech enhancement, e.g. noise reduction or echo cancellation reducing echo effects in line transmission systems H04B3/20; echo suppression in hands-free telephones H04M9/08

Abstract

A system and method facilitating signal enhancement utilizing mixture models is provided. The invention includes a signal enhancement adaptive system having a speech model, a noise model and a plurality of adaptive filter parameters. The signal enhancement adaptive system employs probabilistic modeling to perform signal enhancement of a plurality of windowed frequency transformed input signals received, for example, for an array of microphones. The signal enhancement adaptive system incorporates information about the statistical structure of speech signals. The signal enhancement adaptive system can be embedded in an overall enhancement system which also includes components of signal windowing and frequency transformation.

Claims

1. A computer implemented signal enhancement system, comprising the following computer executable components:

a speech model that characterizes statistical properties of speech;

a noise model that characterizes statistical properties of noise;

a windowed component that applies an N-point window to input signals;

a frequency transformation component that receives a windowed signal output from the windowed component and computes a frequency transform of the windowed signal to generate a plurality of frequency transformed input signals; and

a plurality of adaptive filter parameters utilized by the signal enhancement adaptive system to provide an enhanced signal output, the enhanced signal output being based, at least in part, upon the plurality of frequency transformed input signals, the plurality of adaptive filter parameters being modified based, at least in part, upon the speech model, the noise model and the enhanced signal output.

2. The signal enhancement system of claim 1, the speech model employing, at least in part, the equations:

$p<br><br>\left(X|S\right)=\underset{m}{\overset{}{\prod <br><br>}}<br><br>p<br><br>\left(X_m|S_m\right),p<br><br>\left(S\right)=\underset{m}{\overset{}{\prod <br><br>}}<br><br>p<br><br>\left(S_m\right)$

where S are speech components of the speech model,

X are speech signals corresponding to the speech components,

X_m is a subband signal of the enhanced signal output at frame m, and,

S_m is a component of the speech model at frame m.

3. The signal enhancement system of claim 1, the noise model employing, at least in part, the equation:

$p<br><br>\left(Y_m^i|X\right)=\underset{k}{\overset{}{\prod <br><br>}}<br><br>\mathrm{??}<br><br>\left(Y_m^i<br><br>\left[k\right]|\underset{n}{\sum <br><br>}<br><br>H_n^i<br><br>\left[k\right]<br><br>X_{m-n}<br><br>\left[k\right],B^i<br><br>\left[k\right]\right)$

wherein Y_mⁱ is one of the frequency transformed input signals at frame m,

X are speech signals corresponding to speech components,

Y_mⁱ[k] is a subband of one of the frequency transformed input signals at frame m,

H_nⁱ[k] is one of the plurality of adaptive filter parameters;

X_m-n[k] is a subband of a time delay of speech signals corresponding to speech components; and

,

Bⁱ[k] is the noise model.

4. The signal enhancement system of claim 1, modification of at least one of the plurality of adaptive filter parameters being based upon a variational method.

5. The signal enhancement system of claim 1, modification of at least one of the plurality of adaptive filter parameters being based, at least in part, upon the equation:

$v_{\mathrm{sm}}<br><br>\left[k\right]=\underset{m}{\sum <br><br>}<br><br>B^i<br><br>\left[k\right]|H_{n-m}^i<br><br>\left[k\right]<br><br>{|}^2<br><br>+A_s<br><br>\left[k\right]$

wherein ν

_sm[k] is the precision of X_m[k], wherein X_m[k] is the enhanced signal output,

Bⁱ[k] is the noise model,

H_n-mⁱ[k] is one of the plurality of adaptive filter parameters; and

,

A_s[k] is the precision of a component s of the speech model.

6. The signal enhancement system of claim 1, modification of at least one of the plurality of adaptive filter parameters being based upon a variational expectation maximization algorithm having an expectation step (E-step) and an maximization step (M-step).

7. The signal enhancement system of claim 6, the E-step being based, at least in part, upon the equations:

$H_{n-m}^i<br><br>\left[k\right]$

wherein ν

_sm[k] is the precision of the enhanced signal output,

ρ

_sm[k] is the mean of the enhanced signal output,

Bⁱ[k] is the noise model,

Y_mⁱ[k] is a subband of one of the frequency transformed input signals at frame m,

H_n-mⁱ[k] is one of the plurality of adaptive filter parameters

{circumflex over (X)}_r is the enhanced signal output; and

,

A_s[k] is the precision of a component s of the speech model.

8. The signal enhancement system of claim 1, the noise model being trained on a large dataset of clean speech, at least in part, off-line.

9. The signal enhancement system of claim 1, the noise model being trained on a large dataset of clean speech, at least in part, during a quiet period of at least one of the plurality of frequency transformed input signals.

10. The signal enhancement system of claim 1, the noise model being trained on a large dataset of clean speech, at least in part, during operation of the signal enhancement adaptive model.

11. A computer implemented signal enhancement system, comprising the following computer executable components:

a frequency transformation component that receives windowed signal inputs, computes a frequency transform of the windowed signals, and provides outputs of frequency transformed windowed signals; and

,

a signal enhancement adaptive system that receives the frequency transformed windowed signals from the frequency transformation component and provides an enhanced signal output, the enhanced signal output being based, at least in part, upon the frequency transformed windowed signals;

wherein the signal enhancement adaptive system has a speech model, a noise model and a plurality of adaptive filter parameters also utilized to provide an enhanced signal output, the plurality of adaptive filter parameters being modified based, at least in part, upon the speech model, the noise model and the enhanced signal output.

12. The system of claim 11, further comprising a windowing component that applies an N-point window to input signals and provides the windowed signal inputs to the frequency transformation component.

13. The system of claim 11, further comprising at least two audio input devices that provide the input signals.

14. The system of claim 13, at least one of the two audio input devices being a microphone.

15. The system of claim 11, the frequency transform being a Fast Fourier Transform.

16. A computer implemented method for speech signal enhancement, comprising the following computer executable acts:

receiving input signals;

windowing the input signals;

performing a frequency transform of the windowed input signals to generate a plurality of frequency transformed input signals;

utilizing a signal enhancement adaptive model having a speech model and a noise model;

providing a plurality of adaptive filter parameters utilized to provide an enhanced signal output, the enhanced signal output based on the plurality of the frequency transformed input signals; and

modifying at least one of the adaptive filter parameters based, at least in part, upon the speech model, the noise model and the enhanced signal output.

17. The method of claim 16, further comprising at least one of the following acts:

training the speech model on a large dataset of clean speech,

training the noise model offline from quiet moments in a noisy signal and online using expectation maximization on a full microphone signal.

18. A computer implemented method for speech signal enhancement, comprising the following computer executable acts:

calculating an enhanced signal output based on a plurality of adaptive filter parameters;

for each frame and subband, calculating a conditional mean of the enhanced signal output;

for each frame and subband, calculating a conditional precision of the enhanced signal output;

for each frame and subband, calculating a conditional probability of a speech model;

calculating an autocorrelation of the enhanced signal output;

calculating a cross correlation of the enhanced signal output; and

,

modifying at least one of the plurality of adaptive filter parameters based on the autocorrelation and cross correlation of the enhanced signal output.

19. A computer readable medium having stored thereon a data structure, comprising:

a first data field comprising a speech model that characterizes statistical properties of speech;

a second data field comprising a noise model that characterizes statistical properties of noise;

a third data field comprising a windowed component that applies an N-point window to input signals;

a fourth data field comprising a frequency transformation component that receives a windowed signal output from the windowed component and computes a frequency transform of the windowed signal to generate a plurality of frequency transformed input signals;

a fifth data field comprising an enhanced signal output being based, at least in part, upon the plurality of frequency transformed input signals; and

a sixth data field comprising a plurality of adaptive filter parameters, at least one of the plurality of adaptive filter parameters having been modified based, at least in part, upon the enhanced signal output, the speech model and the noise model.

20. A computer readable medium storing computer executable components of a signal enhancement model, comprising:

a speech model component that models speech;

a noise model component that models noise;

a windowed component that applies an N-point window to input signals; and

a frequency transformation component that receives a windowed signal output from the windowed component and computes a frequency transform of the windowed signal to generate a plurality of frequency transformed input signals;

the signal enhancement model utilizing a plurality of adaptive filter parameters to provide an enhanced signal output, the enhanced signal output being based, at least in part upon, the plurality of frequency transformed input signals, the plurality of adaptive filter parameters being modified based, at least in part, upon the speech model, the noise model and the enhanced signal output.

21. A computer implemented signal enhancement system, comprising:

computer implemented means for windowing a plurality of input signals;

computer implemented means for frequency transforming the plurality of windowed input signals;

computer implemented means for receiving the frequency transformed windowed signals;

computer implemented means for providing an enhanced signal output based, at least in part, upon the frequency transformed windowed signals;

computer implemented means for modeling speech;

computer implemented means for modeling noise;

computer implemented means for providing a plurality of adaptive filter parameters; and

,

computer implemented means for modifying the plurality of adaptive filter parameters, the modification being based, at least in part, upon the means for modeling speech, the means for modeling noise and the enhanced signal output.