Method, apparatus, mobile terminal and computer program product for providing efficient evaluation of feature transformation

• US 7,480,641 B2
• Filed: 04/07/2006
• Issued: 01/20/2009
• Est. Priority Date: 04/07/2006
• Status: Active Grant

• Current Assignee: HMD Global Oy
• Original Assignee: Nokia Corporation
• Inventors: Popa, Victor, Tian, Jilei, Nurminen, Jani K.
• Primary Examiner(s): Holmes, Michael B
• Application Number:
  US11/400,629
• Publication Number:
  US 20070239634A1
• Time in Patent Office: 1,019 Days
• Field of Search: None
• US Class Current: 706/15
• CPC Class Codes: G10L 13/033 Voice editing, e.g. manipulating the voice of the synthesiser
• CPC Class Codes: G10L 2021/0135 Voice conversion or morphing
• CPC Class Codes: G10L 21/00 Speech or voice signal processing techniques to produce another audible or non-audible signal, e.g. visual or tactile, in order to modify its quality or its intelligibility G10L19/00 takes precedence

Abstract

An apparatus for providing efficient evaluation of feature transformation includes a training module and a transformation module. The training module is configured to train a Gaussian mixture model (GMM) using training source data and training target data. The transformation module is in communication with the training module. The transformation module is configured to produce a conversion function in response to the training of the GMM. The training module is further configured to determine a quality of the conversion function prior to use of the conversion function by calculating a trace measurement of the GMM.

Claims

1. A method comprising:

training a Gaussian mixture model (GMM) using training source data and training target data;

producing a conversion function in response to the training;

determining a quality of the conversion function prior to use of the conversion function by calculating a trace measurement of the GMM; and

selectively using the conversion function for feature transformation based on the trace measurement.

2. A method according to claim 1, further comprising thereafter, converting source data input into target data output using the conversion function.

3. A method according to claim 1, wherein training the GMM comprises training the GMM using training source voice data and training target voice data.

4. A method according to claim 3, further comprising an initial operation of recording the training target voice data to correspond to previously recorded training source voice data.

5. A method according to claim 1, wherein the trace measurement is calculated using the equation Q=∫

ε

(x)·

p(x)·

dx.

6. A method according to claim 1, wherein the trace measurement is calculated using the approximation

$Q\approx$

∑

l = 1 L ⁢

⁢

w l ·

tr ( Σ

l yy ⁢

) .

7. A method according to claim 1, further comprising comparing the trace measurement to a threshold.

8. A method according to claim 7, further comprising modifying the conversion function in response to the comparison of the trace measurement to the threshold.

9. A method according to claim 7, further comprising varying the threshold based on one or more of:

a number of mixtures;

a number of dimensions;

known statistical properties of data; and

a range of data.

10. A method according to claim 1, further comprising calculating a plurality of trace measurements corresponding to a plurality of conversion functions based on corresponding different GMMs and selecting one of the conversion functions having a lowest trace measurement for use in converting the source data input into the target data output.

11. A computer program product comprising at least one computer-readable storage medium having computer-readable program code portions stored therein, the computer-readable program code portions comprising:

a first executable portion for training a Gaussian mixture model (GMM) using training source data and training target data;

a second executable portion for producing a conversion function in response to the training;

a third executable portion for determining a quality of the conversion function prior to use of the conversion function by calculating a trace measurement of the GMM; and

a fourth executable portion for selectively using the conversion function for feature transformation based on the trace measurement.

12. A computer program product according to claim 11, further comprising a fifth executable portion for thereafter, converting source data input into target data output using the conversion function.

13. A computer program product according to claim 11, wherein the first executable portion includes instructions for training the GMM using training source voice data and training target voice data.

14. A computer program product according to claim 13, further comprising a fifth executable portion for performing an initial operation of recording the training target voice data to correspond to previously recorded training source voice data.

15. A computer program product according to claim 11, wherein the trace measurement is calculated using the approximation

$Q\approx$

∑

l = 1 L ⁢

⁢

w l ·

tr ( Σ

l yy ⁢

) .

16. A computer program product according to claim 11, further comprising a fifth executable portion for comparing the trace measurement to a threshold.

17. A computer program product according to claim 16, wherein the fifth executable portion includes instructions for modifying the conversion function in response to the comparison of the trace measurement to the threshold.

18. A computer program product according to claim 16, wherein the fifth executable portion includes instructions for varying the threshold based on one or more of:

a number of mixtures;

a number of dimensions;

known statistical properties of data; and

a range of data.

19. A computer program product according to claim 11, further comprising a fifth executable portion for calculating a plurality of trace measurements corresponding to a plurality of conversion functions based on corresponding different GMMs and selecting one of the conversion functions having a lowest trace measurement for use in converting the source data input into the target data output.

20. An apparatus comprising a processor configured to control:

a training module configured to train a Gaussian mixture model (GMM) using training source data and training target data; and

a transformation module in communication with the training module, the transformation module being configured to produce a conversion function in response to the training of the GMM,

wherein the training module is further configured to determine a quality of the conversion function prior to use of the conversion function by calculating a trace measurement of the GMM.

21. An apparatus according to claim 20, wherein transformation module is further configured to convert source data input into target data output using the GMM.

22. An apparatus according to claim 20, wherein training module is further configured to train the GMM using training source voice data and training target voice data.

23. An apparatus according to claim 22, wherein the training target voice data is recorded to correspond to previously recorded training source voice data.

24. An apparatus according to claim 20, wherein the trace measurement is calculated using the equation Q=∫

ε

(x)·

p(x)·

dx.

25. An apparatus according to claim 20, wherein the trace measurement is calculated using the approximation

$Q\approx$

∑

l = 1 L ⁢

⁢

w l ·

tr ( Σ

l yy ⁢

) .

26. An apparatus according to claim 20, wherein the training module is configured to compare the trace measurement to a threshold.

27. An apparatus according to claim 26, wherein the transformation module is configured to modify the conversion function in response to the comparison of the trace measurement to the threshold.

28. An apparatus according to claim 26, wherein the training module is configured to vary the threshold based on one or more of:

a number of mixtures;

a number of dimensions;

known statistical properties of data; and

a range of data.

29. An apparatus according to claim 20, wherein the training module is further configured to calculate a plurality of trace measurements corresponding to a plurality of conversion functions based on corresponding different GMMs and selecting one of the conversion functions having a lowest trace measurement for use in converting the source data input into the target data output.

30. A mobile terminal comprising a processor configured to control:

a training module configured to train a Gaussian mixture model (GMM) using training source data and training target data; and

a transformation module in communication with the training module, the transformation module being configured to produce a conversion function in response to the training of the GMM and thereafter, convert source data input into target data output using the GMM,

wherein the training module is further configured to determine a quality of the conversion function prior to use of the conversion function by calculating a trace measurement of the GMM, and wherein the processor is configured to selectively use the conversion function for feature transformation based on the trace measurement.

31. A mobile terminal according to claim 30, wherein training module is further configured to train the GMM using training source voice data and training target voice data.

32. A mobile terminal according to claim 31, wherein the training target voice data is recorded to correspond to previously recorded training source voice data.

33. A mobile terminal according to claim 30, wherein the training module is configured to compare the trace measurement to a threshold.

34. A mobile terminal according to claim 30, wherein the training module is further configured to calculate a plurality of trace measurements corresponding to a plurality of conversion functions based on corresponding different GMMs and selecting one of the conversion functions having a lowest trace measurement for use in converting the source data input into the target data output.

35. An apparatus comprising:

a means for training a Gaussian mixture model (GMM) using training source data and training target data;

a means for producing a conversion function in response to the training; and

a means for determining a quality of the conversion function prior to use of the conversion function by calculating a trace measurement of the GMM; and

means for selectively using the conversion function for feature transformation based on the trace measurement.

36. An apparatus comprising a processor configured to:

train a Gaussian mixture model (GMM) using training source data and training target data;

produce a conversion function in response to the training;

determine a quality of the conversion function prior to use of the conversion function by calculating a trace measurement of the GMM; and

selectively use the conversion function for feature transformation based on the trace measurement.