Method and apparatus for detecting voice region

• US 7,966,179 B2
• Filed: 01/27/2006
• Issued: 06/21/2011
• Est. Priority Date: 02/04/2005
• Status: Expired due to Fees

• Current Assignee: Samsung Electronics Co. Ltd.
• Original Assignee: Samsung Electronics Co. Ltd.
• Inventors: Oh, Kwang-cheol, Park, Ki-young
• Primary Examiner(s): Dorvil; Richemond
• Assistant Examiner(s): Borsetti; Greg
• Application Number:
  US11/340,693
• Publication Number:
  US 20060178881A1
• Time in Patent Office: 1,971 Days
• Field of Search: 704/208, 704/E11.003, 704/E11.001, 704/253, 704/248, 704/233
• 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 with a voice region detecting apparatus, the method comprising:

converting an input voice signal representing at least a physical voice into a frequency domain signal by preprocessing the input voice signal;

performing sigmoid compression on the converted signal;

transforming at least one component of a spectrum vector generated by the sigmoid compression into a scalar voice detection parameter wherein the transforming is performed using the equation

2. The method as set forth in claim 1, further comprising maintaining consonant parameter values similar to those of vowel parameter values by low-pass-filtering the converted frequency domain signal and providing the low-pass-filtered signal as an input for the sigmoid compression.

3. The method as set forth in claim 1, wherein the converting of the input voice signal comprises:

pre-emphasizing the input voice signal;

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

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

4. The method as set forth in claim 1, wherein the sigmoid compression is performed using the equation:

5. The method as set forth in claim 4, wherein α

is a constant that is less than 1.

6. The method as set forth in claim 4, wherein μ

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

7. The method as set forth in claim 4, wherein μ

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

8. The method as set forth in claim 4, wherein β

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

9. An apparatus for detecting a voice region including a processor having computing device-executable instructions, 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 wherein the parameter generation unit performs a vector-to-scalar transformation using the equation

10. The apparatus as set forth in claim 9, further comprising a low-pass filtering unit to maintain consonant parameter values similar to those of vowel parameter values by low-pass-filtering the converted frequency domain signal and providing the low-pass-filtered signal as an input for the sigmoid compression.

11. The apparatus as set forth in claim 9, 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.

12. The apparatus as set forth in claim 9, wherein the sigmoid compression unit performs the sigmoid compression according to the equation:

13. The apparatus as set forth in claim 12, wherein α

is a constant that is less than 1.

14. The apparatus as set forth in claim 12, wherein μ

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

15. The apparatus as set forth in claim 12, wherein μ

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

16. The apparatus as set forth in claim 12, wherein β

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

17. A non-transitory computer-readable storage media storing computer-readable code for implementation of a method of detecting a voice region, the method comprising:

converting an input voice signal representing at least a physical voice into a frequency domain signal by preprocessing the input voice signal;

performing sigmoid compression on the converted signal;

transforming at least one component of a spectrum vector generated by the sigmoid compression into a scalar voice detection parameter wherein the transforming is performed using the equation