Method and apparatus for detecting voice region

• US 20060178881A1
• Filed: 01/27/2006
• Published: 08/10/2006
• Est. Priority Date: 02/04/2005
• Status: Active Grant

• Current Assignee: Samsung Electronics Co. Ltd.
• Original Assignee: Samsung Electronics Co. Ltd.
• Inventors: Oh, Kwang-cheol, Park, Ki-young
• Granted Patent: US 7,966,179 B2
• Time in Patent Office: Days
• US Class Current: 704/233
• CPC Class Codes: G10L 25/78 Detection of presence or absence of voice signals switching of direction of transmission by voice frequency in two-way loud-speaking telephone systems H04M9/10

Abstract

A method and apparatus for distinguishing a voice region from a non-voice region in an environment where various types of noise and voice are mixed together are provided. The method includes the steps of converting an input voice signal into a frequency domain signal by preprocessing the input voice signal, performing sigmoid compression on the converted signal, transforming a spectrum vector generated by the sigmoid compression into a voice detection parameter in scalar form, and detecting the voice region using the parameter.

Claims

1. A method of detecting a voice region, comprising the steps of:

(a) converting an input voice signal into a frequency domain signal by preprocessing the input voice signal;

(b) performing sigmoid compression on the converted signal;

(c) transforming a spectrum vector generated by the sigmoid compression into a scalar voice detection parameter; and

(d) detecting the voice region using the parameter.

2. The method as set forth in claim 1, further comprising the step of low-pass-filtering the converted frequency domain signal and providing the low-pass-filtered signal as an input for sigmoid compression.

3. The method as set forth in claim 1, wherein step (d) comprises the step of comparing the parameter with a predetermined threshold value and determining that the region in which the parameter exceeds the threshold value is a voice region.

4. The method as set forth in claim 1, wherein step (a) comprises:

the step of pre-emphasizing the input voice signal;

the step of applying a predetermined window to the pre-emphasized signal; and

the step of Fourier transforming the signal to which the window has been applied.

5. The method as set forth in claim 1, wherein step (b) is performed using the equation:

6. The method as set forth in claim 5, wherein α

is a constant that is less than 1.

7. The method as set forth in claim 5, wherein μ

is acquired by taking a sample average from current frames irrespective of a voice region.

8. The method as set forth in claim 5, wherein μ

is acquired by taking a sample average from frames in a non-voice region for respective frequencies.

9. The method as set forth in claim 5, wherein β

is an approximate inverse of an average of a spectrum that includes a voice.

10. The method as set forth in claim 1, wherein step (c) is performed using the equation:

11. An apparatus for detecting a voice region, the apparatus comprising:

a pre-processing unit for converting an input voice signal into a frequency domain signal by preprocessing the input voice signal;

a sigmoid compression unit for performing sigmoid compression on the converted signal;

a parameter generation unit for transforming a spectrum vector generated by the sigmoid compression into a scalar voice detection parameter; and

a voice region detection unit for detecting the voice region using the parameter.

12. The apparatus as set forth in claim 11, further comprising a low-pass filtering unit for low-pass-filtering the converted frequency domain signal and providing the low-pass-filtered signal as an input for sigmoid compression.

13. The apparatus as set forth in claim 11, wherein the voice region detection unit compares the parameter with a predetermined threshold value and determines a region in which the parameter exceeds the threshold value to be a voice region.

14. The apparatus as set forth in claim 11, wherein the pre-processing unit pre-emphasizes the input voice signal, applies a predetermined window to the pre-emphasized signal, and Fourier transforms the signal to which the window has been applied.

15. The apparatus as set forth in claim 11, wherein the sigmoid compression unit performs the sigmoid compression according to the equation:

16. The apparatus as set forth in claim 15, wherein α

is a constant that is less than 1.

17. The apparatus as set forth in claim 15, wherein μ

is acquired by taking a sample average from current frames irrespective of a voice region.

18. The apparatus as set forth in claim 15, wherein μ

is acquired by taking a sample average from frames in a non-voice region for respective frequencies.

19. The apparatus as set forth in claim 15, wherein β

is an approximate inverse of an average of a spectrum that includes a voice.

20. The apparatus as set forth in claim 11, wherein the parameter generation unit performs a vector-to-scalar transformation using the equation: