Method and apparatus for handset detection

• US 6,778,957 B2
• Filed: 08/21/2001
• Issued: 08/17/2004
• Est. Priority Date: 08/21/2001
• Status: Expired due to Term

• Current Assignee: Nuance Communications, Inc. (Microsoft Corporation)
• Original Assignee: International Business Machines Corporation
• Inventors: Wang, Zhong-Hua, Lubensky, David, Wu, Cheng
• Primary Examiner(s): Dorvil, Richemond
• Assistant Examiner(s): Lerner, Martin
• Application Number:
  US09/934,157
• Publication Number:
  US 20030065514A1
• Time in Patent Office: 1,092 Days
• Field of Search: 704/231, 704/233, 704/236, 704/238, 704/239, 704/246
• US Class Current: 704/233
• CPC Class Codes: G10L 17/02 Preprocessing operations, e.g. segment selection; Pattern representation or modelling, e.g. based on linear discriminant analysis [LDA] or principal components; Feature selection or extraction
• CPC Class Codes: G10L 17/20 Pattern transformations or operations aimed at increasing system robustness, e.g. against channel noise or different working conditions

Abstract

Disclosed is a method of automated handset identification, comprising receiving a sample speech input signal from a sample handset; deriving a cepstral covariance sample matrix from said first sample speech signal; calculating, with a distance metric, all distances between said sample matrix and one or more cepstral covariance handset matrices, wherein each said handset matrix is derived from a plurality of speech signals taken from different speakers through the same handset; and determining if the smallest of said distances is below a predetermined threshold value.

Claims

1. A method of automated handset identification, comprising:

receiving a sample speech input signal from a sample handset;

deriving a cepstral covariance sample matrix from said first sample speech signal;

calculating, with a distance metric, all distances between said sample matrix and one or more cepstral covariance handset matrices, wherein each said handset matrix is derived from a plurality of speech signals taken from different speakers through the same handset; and

determining if the smallest of said distances is below a predetermined threshold value.

2. The method of claim 1 wherein said distance metric satisfies symmetry and positivity conditions.

3. The method of claim 2 wherein said distance metric is selected from:

$d_1<br><br>\left(S,\mathrm{\Sigma <br><br>}\right)=\frac{A}{H}-1,\text{\hspace{1em}<br><br>}<br><br>d_5<br><br>\left(S,\mathrm{\Sigma <br><br>}\right)=A+\frac{1}{\stackrel{\_}{H}}-2,d_6<br><br>\left(S,\mathrm{\Sigma <br><br>}\right)=\left(A+\frac{1}{\stackrel{\_}{H}}\right)<br><br>\left(G+\frac{1}{G}\right)-4,\text{\hspace{1em}<br><br>}<br><br>d_7<br><br>\left(S,\mathrm{\Sigma <br><br>}\right)=\frac{A}{\stackrel{\_}{2<br><br>H}}<br><br>\left(G+\frac{1}{G}\right)-1,d_8<br><br>\left(S,\mathrm{\Sigma <br><br>}\right)=\frac{\left(A+\frac{1}{\stackrel{\_}{H}}\right)}{\left(G+\frac{1}{G}\right)}-1,\text{\hspace{1em}<br><br>}<br><br>d_9<br><br>\left(S,\mathrm{\Sigma <br><br>}\right)=\frac{A}{\stackrel{\_}{G}}+\frac{G}{H}-2,$

and fusion derivatives thereof.

4. The method of claim 1 wherein said handset matrices are stored in a database of handset matrices wherein each handset matrix is derived from a unique make and model of handset.

5. The method of claim 1 wherein said different speakers number ten or more.

6. The method of claim 5 wherein the number of said different speakers is no less than twenty.

7. A program storage device, readable by machine, tangibly embodying a program of instructions executable by the machine to perform method steps for automated handset identification, said method steps comprising:

receiving a sample speech input signal from a sample handset;

deriving a cepstral covariance sample matrix from said first sample speech signal;

calculating, with a distance metric, all distances between said sample matrix and one or more cepstral covariance handset matrices, wherein each said handset matrix is derived from a plurality of speech signals taken from different speakers through the same handset; and

determining if the smallest of said distances is below a predetermined threshold value.

8. The apparatus of claim 7 wherein said distance metric satisfies symmetry and positivity conditions.

9. The apparatus of claim 8 wherein said distance metric is selected from:

$d_1<br><br>\left(S,\mathrm{\Sigma <br><br>}\right)=\frac{A}{H}-1,\text{\hspace{1em}<br><br>}<br><br>d_5<br><br>\left(S,\mathrm{\Sigma <br><br>}\right)=A+\frac{1}{\stackrel{\_}{H}}-2,d_6<br><br>\left(S,\mathrm{\Sigma <br><br>}\right)=\left(A+\frac{1}{\stackrel{\_}{H}}\right)<br><br>\left(G+\frac{1}{G}\right)-4,\text{\hspace{1em}<br><br>}<br><br>d_7<br><br>\left(S,\mathrm{\Sigma <br><br>}\right)=\frac{A}{\stackrel{\_}{2<br><br>H}}<br><br>\left(G+\frac{1}{G}\right)-1,d_8<br><br>\left(S,\mathrm{\Sigma <br><br>}\right)=\frac{\left(A+\frac{1}{\stackrel{\_}{H}}\right)}{\left(G+\frac{1}{G}\right)}-1,\text{\hspace{1em}<br><br>}<br><br>d_9<br><br>\left(S,\mathrm{\Sigma <br><br>}\right)=\frac{A}{\stackrel{\_}{G}}+\frac{G}{H}-2,$

and fusion derivatives thereof.

10. The apparatus of claim 7 wherein said handset matrices are stored in a database of handset matrices wherein each handset matrix is derived from a unique make and model of handset.

11. The apparatus of claim 7 wherein said different speakers number ten or more.

12. The apparatus of claim 11 wherein the number of said different speakers is no less than twenty.

13. An automated handset identification system, comprising:

means for receiving a sample speech input signal from a sample handset;

means for deriving a cepstral covariance sample matrix from said first sample speech signal;

means for calculating, with a distance metric, all distances between said sample matrix and one or more cepstral covariance handset matrices, wherein each said handset matrix is derived from a plurality of speech signals taken from different speakers through the same handset; and

means for determining if the smallest of said distances is below a predetermined threshold value.

14. The system of claim 13 wherein said means for receiving sample speech is in communication with an incoming line of communication.

15. The system of claim 14 wherein said incoming line of communication is a phone line.