Powering-up AFE and microcontroller after comparing analog and truncated sounds

Patent metadata

Field	Value
Publication number	US-9460720-B2
Application number	US-201314013012-A
Country	US
Kind code	B2
Filing date	Aug 28, 2013
Priority date	Aug 28, 2013
Publication date	Oct 4, 2016
Grant date	Oct 4, 2016

Abstract

A low power sound recognition sensor is configured to receive an analog signal that may contain a signature sound. The received analog signal is evaluated using a detection portion of the analog section to determine when background noise on the analog signal is exceeded. A feature extraction portion of the analog section is triggered to extract sparse sound parameter information from the analog signal when the background noise is exceeded. An initial truncated portion of the sound parameter information is compared to a truncated sound parameter database stored locally with the sound recognition sensor to detect when there is a likelihood that the expected sound is being received in the analog signal. A trigger signal is generated to trigger classification logic when the likelihood that the expected sound is being received exceeds a threshold value.

First claim

What is claimed is:

1. A process of operating a sound recognition system comprising:
(a) placing an analog front end channel and a microcontroller in a low power mode;
(b) receiving analog sound signals in signal trigger logic;
(c) comparing the analog sound signals to a reference voltage and producing a sound detected control signal from the signal trigger logic when an analog sound signal exceeds the reference voltage;
(d) powering up the analog front end channel in response to the sound detected control signal while maintaining the microcontroller in a low power mode;
(e) pre-screening the analog sound signals in the analog front end channel including comparing a truncated version of the analog sound signals to stored truncated sound signatures and producing an event trigger signal from the analog front end upon detecting a match of a truncated version of the analog sound signal and a stored truncated sound signature; and
(f) powering up the microcontroller in response to the event trigger signal.

2. The process of claim 1 in which the comparing includes amplifying the received analog sound signals and comparing the amplified analog sound signals to the reference voltage.

3. The process of claim 1 in which the prescreening includes amplifying the received analog sound signals and extracting frame based features of the amplified analog sound signals.

4. The process of claim 1 in which the prescreening includes amplifying the received analog sound signals, extracting truncated frame based sound features of the amplified analog sound signals, and buffering an initial truncated set of several frames of the truncated sound features.

5. The process of claim 4 in which the buffering includes buffering five frames of the truncated sound features that represent 20 milliseconds of the analog sound signals.

6. The process of claim 1 including processing the truncated version of the received analog sound signals in the microcontroller after powering up the microcontroller.

7. A sound recognition system comprising:
(a) a microphone;
(b) signal trigger and control logic having a microphone input coupled to the microphone to receive analog sound signals from the microphone, a reference voltage input, a power up signal output, an event trigger input, and a first microcontroller output;
(c) an analog front end channel having an input coupled to the microphone to receive analog sound signals from the microphone, a power up input coupled to the power up output, an event trigger output coupled to the event trigger input, and a second microcontroller output; and
(d) microcontroller circuitry having a first input coupled to the first microcontroller output and a second input coupled to the second microcontroller output.

8. The system of claim 7 in which the signal trigger and control logic includes comparator circuitry having an input coupled to the microphone input, an input coupled to the reference voltage input, and a sound trigger output.

9. The system of claim 7 in which the signal trigger and control logic includes control circuitry having a sound trigger input, the power up output, the event trigger input, and the first microcontroller output.

10. The system of claim 7 in which the signal trigger and control logic includes comparator circuitry having an input coupled to the microphone input, an input coupled to the reference voltage input, and a sound trigger output, and control circuitry having a sound trigger input coupled to the sound trigger output, the power up output, the event trigger input, and the first microcontroller output.

11. The system of claim 7 in which the an analog front end channel includes:
analog to digital converter circuitry having an input coupled to the microphone to receive analog sound signals from the microphone and a digital sound signals output;
feature extraction circuitry having an input coupled to the digital sound signals output of the analog to digital converter and having a truncated sound features output, the feature extraction circuitry extracting truncated sound features from the digital sound signals;
buffer circuitry having an input coupled to the truncated sound features output, and a buffered output; and
feature pre-screening circuitry having an input coupled to the buffered output, the power up input, the event trigger output, and the second microcontroller output.

12. The system of claim 11 in which the feature pre-screening circuitry includes stored truncated sound features that can be compared to the truncated sound features from the buffer circuitry.

Assignees

• Texas Instruments Inc

Inventors

• Ma Wei
• Tan Bozhao
• Zhang Zhenyong

Classifications

• G10L25/84

  for discriminating voice from noise · CPC title

• H04R2460/07

  Use of position data from wide-area or local-area positioning systems in hearing devices, e.g. program or information selection · CPC title

• H04R2430/03

  Synergistic effects of band splitting and sub-band processing · CPC title

• G10L15/28 Primary

  Constructional details of speech recognition systems · CPC title

• Y02B60/32

  Cross-Sectional Technologies · mapped topic