Adaptive voice detection method and system

• US 7,664,635 B2
• Filed: 09/08/2005
• Issued: 02/16/2010
• Est. Priority Date: 09/08/2005
• Status: Active Grant

• Current Assignee: Gables Engineering Incorporated
• Original Assignee: Gables Engineering Incorporated
• Inventors: Velandia, Erich, Osmanovic, Nermin
• Primary Examiner(s): MCFADDEN, SUSAN IRIS
• Application Number:
  US11/221,425
• Publication Number:
  US 20070055499A1
• Time in Patent Office: 1,622 Days
• Field of Search: 704/211
• US Class Current: 704/211
• 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 system for detecting a voice signal includes: a first integrator for receiving an input signal and for providing a first integrator output signal, wherein the first integrator includes a first attack time; a second integrator for receiving the input signal and for providing a second integrator output signal, the second integrator including a second attack time that is substantially slower than the first attack time; and a comparator configured for receiving the first and second integrator output signals and for providing a comparator output signal indicating detection of a voice signal when the first integrator output signal exceeds the second integrator output signal by at least a threshold amount.

Claims

1. A system for detecting a voice signal, said system comprising:

a first integrator for receiving an input signal and for providing a first integrator output signal, wherein the first integrator comprises a first attack time;

a second integrator, coupled in parallel with the first integrator, for receiving the input signal and for providing a second integrator output signal, wherein the second integrator comprises a second attack time that is slower than the first attack time; and

a comparator for receiving the first and second integrator output signals and for providing a comparator output signal indicating detection of the voice signal when the first integrator output signal exceeds the second integrator output signal by at least a threshold amount.

2. The system of claim 1, further comprising a gate coupled to the comparator for providing an output comprising the voice signal, in response to receiving the output signal indicating the detection of the voice signal.

3. The system of claim 1, further comprising a buffer for storing samples of the input signal.

4. The system of claim 1, wherein the threshold amount is a 15 Decibels difference between the first and second integrator output signals.

5. The system of claim 2 further comprising a state machine disposed between the comparator and the gate, wherein the state machine comprises an input, to receive the comparator output signal, and an output for setting a release delay such that the gate continues to pass the input signal to the output of the gate during a hold and release delay after the first integrator output signal drops below the threshold level.

6. The system of claim 1 further comprising an analog-to-digital converter for receiving the input signal and providing a digitized version of input signal to the first and second integrators.

7. The system of claim 1 further comprising a speaker coupled to the gate to present an audio signal.

8. The system of claim 3 further comprising an energy calculator disposed between the buffer and the integrators, wherein the energy calculator is for sampling at least a part of the signal stored in the buffer and to provide an energy representation of the signal stored in the buffer to the integrators.

9. A method for detecting voice signals, the method comprising:

coupling a first integrator in parallel with a second integrator;

receiving an input signal at the first and second integrators, wherein the first integrator has a faster response time than the second integrator;

providing, to a comparator, a first integrator output signal and a second integrator output signal;

comparing the first integrator output signal with the second integrator output signal, and

providing a comparator output signal when, during a sampling period, the first integrator output signal exceeds the second integrator output signal by at least a predetermined level, wherein the comparator output signal indicates the presence of a voice signal in the input signal.

10. The method of claim 9 further comprising storing samples of the input signal.

11. The method of claim 10 further comprising storing a window of samples of the input signal for analysis.

12. The method of claim 9 further comprising coupling the input signal to an output in response to detecting a level of the first output signal that exceeds the level of the second signal by a threshold amount.

13. The method of claim 9 further comprising activating a device responsive to the presence of a voice signal in the input signal.

14. The method of claim 13, further comprising deactivating the device in response to detecting that the voice signal is no longer present at the output and after a release delay.

15. A voice activated switch comprising:

a first integrator for receiving an input signal and for providing a first integrator output signal, wherein the first integrator comprises a first attack time;

a second integrator, coupled in parallel with the first integrator, for receiving the input signal and for providing a second integrator output signal, the second integrator comprises a second attack time that is slower than the first attack time;

a comparator for receiving the first and second integrator output signals and for providing a comparator output signal indicating detection of a voice signal when the first integrator output signal exceeds the second integrator output signal by at least a threshold amount; and

a gate coupled to the comparator and for providing an output comprising

an output signal comprising the voice signal, in response to receiving the signal indicating detection of the voice signal.