VAD detection apparatus and method of operation the same

• US 9,830,913 B2
• Filed: 09/22/2015
• Issued: 11/28/2017
• Est. Priority Date: 10/29/2013
• Status: Active Grant

• Current Assignee: Samsung Electronics Co. Ltd.
• Original Assignee: Knowles Electronics Llc (Knowles Corporation)
• Inventors: Thomsen, Henrik, Nandy, Dibyendu
• Primary Examiner(s): ABEBE, DANIEL DEMELASH
• Application Number:
  US14/861,113
• Publication Number:
  US 20160064001A1
• Time in Patent Office: 798 Days
• Field of Search: 704246
• CPC Class Codes: G10L 15/08 Speech classification or search
• CPC Class Codes: G10L 15/22 Procedures used during a speech recognition process, e.g. man-machine dialogue
• 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 19/0204 using subband decomposition
• CPC Class Codes: G10L 2015/088 Word spotting
• CPC Class Codes: G10L 25/21 the extracted parameters being power information
• 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
• CPC Class Codes: H04R 19/04 Microphones H04R19/01 takes precedence
• CPC Class Codes: H04R 3/005 for combining the signals of two or more microphones specially adapted for hearing aids H04R25/407
• CPC Class Codes: H04W 4/16 Communication-related supplementary services, e.g. call-transfer or call-hold

Abstract

A microphone assembly includes an acoustic sensor and a voice activity detector on an integrated circuit coupled to an external-device interface. The acoustic sensor produces an electrical signal representative of acoustic energy detected by the sensor. A filter bank separates data representative of the acoustic energy into a plurality of frequency bands. A power tracker obtains a power estimate for at least one band, including a first estimate based on relatively fast changes in a power metric of the data and a second estimate based on relatively slow changes in a power metric of the data. The presence of voice activity in the electrical signal is based upon the power estimate.

Claims

1. A method in a microphone assembly including an acoustic sensor and a voice activity detector on an integrated circuit coupled to an external-device interface of the microphone assembly, the method comprising:

receiving acoustic energy at the acoustic sensor;

filtering data representative of the acoustic energy into a plurality of bands;

obtaining a power estimate for at least one of the plurality of bands,

the power estimate including a first estimate based on relatively fast changes in a power metric of the data representative of the acoustic energy and a second estimate based on relatively slow changes in a power metric of the data representative of the acoustic energy;

determining whether voice activity is present in the acoustic energy based on the power estimate for the at least one band.

2. The method of claim 1, further comprising,

determining a ratio of the first estimate and the second estimate of a corresponding band;

and

determining whether voice activity is present in the acoustic energy based on a comparison of the ratio to a predetermined threshold.

3. The method of claim 1,

obtaining a power estimate for each of the plurality of bands, each power estimate including a first estimate based on relatively fast changes in a power metric of the data representative of the acoustic energy and a second estimate based on relatively slow changes in a power metric of the data representative of the acoustic energy;

determining multiple ratios based on the first estimate and the second estimate of the plurality of bands;

determining whether voice activity is present in the acoustic energy based on a comparison of the multiple ratios to predetermined thresholds.

4. The method of claim 3, further comprising summing results of the comparisons and determining whether voice activity is present in the acoustic energy based on the summation of results.

5. The method of claim 3, determining the multiple ratios includes determining at least one ratio using the first estimate and the second estimate obtained for the same band.

6. The method of claim 3, determining the multiple ratios includes determining at least one ratio using the first estimate obtained for one band and the second estimate obtained for another band.

7. The method of claim 1, providing an interrupt signal at the external-device interface upon determining that voice activity is present in the acoustic energy.

8. A microphone assembly having an external-device interface, the microphone assembly comprising:

an acoustic sensor having an acoustic input and an electrical output;

a filter bank having an input coupled to the electrical output of the transducer, the filter bank configured to filter data representative of energy detected by the acoustic sensor into a plurality of frequency bands;

a power tracker having an input coupled to an output of the filter bank, the power tracker configured to obtain a power estimate for at least one of the plurality of frequency bands, the power estimate including a first estimate based on relatively fast changes in a power metric of the data representative of the acoustic energy and a second estimate based on relatively slow changes in a power metric of the data representative of the acoustic energy;

a comparison entity coupled to the output of the power tracker, the comparison entity configured to determine whether voice activity is present in the data representative of acoustic energy based upon the power estimate; and

a signal generator configured to generate a wake up signal upon determining that voice activity is present in the data representative of acoustic energy.

9. The microphone assembly of claim 8,

the power tracker configured to determine a ratio of the first estimate and the second estimate of a corresponding frequency band, and

the comparison entity configured to determine whether voice activity is present in the acoustic energy based on a comparison of the ratio to a predetermined threshold.

10. The microphone assembly of claim 8,

the power tracker configured to obtain a power estimate for each of the plurality of frequency bands, each power estimate including a first estimate based on relatively fast changes in a power metric of the data representative of the acoustic energy and a second estimate based on relatively slow changes in a power metric of the data representative of the acoustic energy,

the power tracker configured to determine multiple ratios based on the first estimate and the second estimate of the plurality of frequency bands,

the comparison entity configured to determine whether voice activity is present in the acoustic energy based on a comparison of the multiple ratios to predetermined thresholds.

11. The microphone assembly of claim 10, the comparison entity configured to sum results of the comparisons and to determine whether voice activity is present in the acoustic energy based on the summation of results.

12. The microphone assembly of claim 10, at least one of the multiple ratios includes a ratio of the first estimate and the second estimate for the same frequency band.

13. The microphone assembly of claim 10, at least one of the multiple ratios includes a ratio of the first estimate obtained for one frequency band and the second estimate obtained for another frequency band.

14. The microphone assembly of claim 8, a signal generator configured to provide the wake up signal at the external-device interface upon determining that voice activity is present in the acoustic energy.

15. The microphone assembly of claim 8, wherein the filter bank, the power tracker, the comparison entity, and the signal generator are implemented on an integrated circuit of the microphone assembly.

16. A microphone assembly having an external-device interface, the microphone assembly comprising:

an acoustic sensor having an acoustic input and an electrical output;

an analog to digital (A/D) converter coupled to the acoustic sensor, the A/D converter configured to generate a data representative of an electrical signal generated by the acoustic sensor;

a processor coupled to the A/D converter, the processor configured to;

filter the data representative of the electrical signal into a plurality of bands;

obtain a power estimate for at least one of the plurality of bands, the power estimate including a first estimate based on relatively fast changes in a power metric of the data representative of the acoustic energy and a second estimate based on relatively slow changes in a power metric of the data representative of the acoustic energy;

determine whether voice activity is present in the data representative of the electrical signal based upon the power estimate; and

generate a wake up signal upon determining that voice activity is present in the data representative of the electrical signal.

17. The microphone assembly of claim 16, the processor further configured to determine a ratio of the first estimate and the second estimate and to determine whether voice activity is present in the data representative of the electrical signal based on a comparison of the ratio to a predetermined threshold.

18. The microphone assembly of claim 16,

the processor configured to obtain a power estimate for each of the plurality of bands, each power estimate including a first estimate based on relatively fast changes in a power metric of the data representative of the acoustic energy and a second estimate based on relatively slow changes in a power metric of the data representative of the acoustic energy,

the processor configured to determine multiple ratios based on the first estimate and the second estimate of the plurality of bands, and

the processor configured to determine whether voice activity is present in the data representative of the electrical signal based on a comparison of the multiple ratios to predetermined thresholds.

19. The microphone assembly of claim 18, the processor configured to sum results of the comparisons and to determine whether voice activity is present in the data representative of the electrical signal based on the summation of results.

20. The microphone assembly of claim 16, the processor configured to provide the wake up signal at the external-device interface upon determining that voice activity is present in the data representative of the electrical signal.