Acoustic Sound Signature Detection Based on Sparse Features

• US 20150063575A1
• Filed: 08/28/2013
• Published: 03/05/2015
• Est. Priority Date: 08/28/2013
• Status: Active Grant

• Current Assignee: Texas Instruments, Inc.
• Original Assignee: Texas Instruments, Inc.
• Inventors: Tan, Bozhao
• Granted Patent: US 9,785,706 B2
• Time in Patent Office: Days
• US Class Current: 381/56
• CPC Class Codes: G06F 1/3203 Power management, i.e. event-based initiation of a power-saving mode
• CPC Class Codes: G06F 16/683 using metadata automatically derived from the content
• CPC Class Codes: G06Q 40/08 Insurance
• CPC Class Codes: G07C 5/085 using electronic data carriers
• CPC Class Codes: G10L 15/00 Speech recognition G10L17/00 takes precedence
• CPC Class Codes: G10L 15/02 Feature extraction for speech recognition; Selection of recognition unit
• CPC Class Codes: G10L 15/22 Procedures used during a speech recognition process, e.g. man-machine dialogue
• CPC Class Codes: G10L 25/00 Speech or voice analysis techniques not restricted to a single one of groups G10L15/00 - G10L21/00 muting semiconductor-based amplifiers when some special characteristics of a signal are sensed by a speech detector, e.g. sensing when no signal is present, H03G3/34
• CPC Class Codes: G10L 25/90 Pitch determination of speech signals
• CPC Class Codes: H04R 29/00 Monitoring arrangements; Testing arrangements for hearing aids H04R25/30; detection of loudspeaker connection H04R5/04; sound-field adaptation dependent on speaker detection H04S7/308
• CPC Class Codes: Y02D 10/00 Energy efficient computing, e.g. low power processors, power management or thermal management

Abstract

A low power sound recognition sensor is configured to receive an analog signal that may contain a signature sound. Sparse sound parameter information is extracted from the analog signal. The extracted sparse sound parameter information is processed using a sound signature database stored in the sound recognition sensor to identify sounds or speech contained in the analog signal, wherein the sound signature database comprises a plurality of sound signatures each representing an entire word or multiword phrase.

Claims

1. A method for operating a sound recognition sensor, the method comprising:

receiving an analog signal that may contain a trigger sound;

extracting sparse sound parameter information from the analog signal using an analog portion of the sound recognition sensor; and

processing the extracted sparse sound parameter information using a sound signature database stored in the sound recognition sensor to identify sounds or speech contained in the analog signal, wherein the sound signature database comprises a plurality of sound signatures each representing an entire word or multiword phrase.

2. The method of claim 1, wherein the sound signature database comprises a plurality of sound signatures each representing a whole spoken word or multiword phrase.

3. The method of claim 1, wherein extracting the sparse sound parameters is performed at a sample rate of less than or equal to approximately 500 samples per second.

4. The method of claim 3, wherein the sample rate is approximately 50 samples per second for voice sounds

5. The method of claim 1, wherein the sparse sound parameter information comprises zero crossing rates, low pass energy values or band pass energy values.

6. An apparatus for recognizing a sound, the apparatus comprising:

a microphone;

an analog front end section comprising analog feature extraction circuitry configured to receive an analog signal from the microphone that may contain a signature sound and to extract sparse sound parameter information from the analog signal;

a digital classification section coupled to the analog front end section being configured to compare the sound parameter information to a sound signature database stored in memory coupled to the digital classification section to detect when the signature sound is received in the analog signal and to generate a match signal when a signature sound is detected, wherein the sound signature database comprises a plurality of sound signatures each representing an entire word or multiword phrase.

7. The apparatus of claim 6, wherein the analog front end is configured to extract the sparse sound parameters at a sample rate of less than or equal to approximately 500 samples per second.

8. The apparatus of claim 7, wherein the sample rate is approximately 50 samples per second.

9. The apparatus of claim 6, wherein the analog feature extraction circuitry comprises:

a counter operable to measure a number of times the analog signal crosses a threshold value during each of a sequence of time frames to form a sequence of zero crossing (ZC) counts; and

a subtractor operable to take a difference between selected pairs of ZC counts to form a sequence of differential ZC counts.

10. The apparatus of claim 6, wherein the analog feature extraction circuitry comprises:

a first counter operable to measure a number of times the analog signal crosses a first threshold value during each a sequence of time frames to form a first zero crossing (ZC) count for each time frame;

a second counter operable to measure a number of times the analog signal crosses a second threshold value during each the sequence of time frames to form a second ZC count for each time frame; and

a subtractor operable to take a difference between the first ZC count and the second ZC count in each time frame to form a sequence of differential ZC counts.

11. The apparatus of claim 6, wherein the analog feature extraction circuitry comprises:

a first counter operable to measure a number of times the analog signal crosses a threshold value by using a first counting clock during each a sequence of first time frames to form a first zero crossing (ZC) count for each time frame;

a second counter operable to measure a number of times the analog signal crosses the threshold value by using a second counting clock during each a sequence of second time frames to form a second ZC count for each time frame, and

a subtractor operable to take a difference between each first ZC count and one of the second ZC counts to form a sequence of differential ZC counts.

12. The apparatus of claim 6, wherein the analog feature extraction circuitry comprises one or more low pass or band pass energy filters.

13. The apparatus of claim 9, wherein the analog feature extraction circuitry further comprises one or more low pass or band pass energy filters.

14. The apparatus of claim 10, wherein the analog feature extraction circuitry further comprises one or more low pass or band pass energy filters.

15. The apparatus of claim 11, wherein the analog feature extraction circuitry further comprises one or more low pass or band pass energy filters.