AUDIO DEVICE FOR RECOGNIZING KEY PHRASES AND METHOD THEREOF

• US 20160232899A1
• Filed: 11/30/2015
• Published: 08/11/2016
• Est. Priority Date: 02/06/2015
• Status: Active Grant

• Current Assignee: Fortemedia, Inc.
• Original Assignee: Fortemedia, Inc.
• Inventors: LIU, Qing Guang, OR, Wilson, LIN, Xiao, CHEN, Lung-Chu Joseph, HUANG, Yen-Son Paul
• Granted Patent: US 9,613,626 B2
• Time in Patent Office: Days
• US Class Current: 1/1
• CPC Class Codes: G10L 15/22 Procedures used during a speech recognition process, e.g. man-machine dialogue
• CPC Class Codes: G10L 2015/027 Syllables being the recognition units
• CPC Class Codes: G10L 2015/088 Word spotting
• CPC Class Codes: G10L 2015/223 Execution procedure of a spoken command
• 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

An audio device and a method thereof are provided. The method is adopted by an audio device to detect a voice, wherein the audio device is coupled to a host device. The method includes an acoustic conversion circuit converting an acoustic wave into an analog audio signal; an analog-to-digital converter (ADC) converting the analog audio signal into digital audio data; a first-level voice detection circuit detecting voice activity in the analog audio signal; a second-level voice detection circuit detecting a beginning syllable of a key phrase in the digital audio data when the voice activity is detected in the digital audio data; and a third-level voice detection circuit detecting the key phrase from the digital audio data only when the beginning syllable of the key phrase is detected in the digital audio data.

Claims

1. An audio device, coupled to a host device, comprising:

an acoustic conversion circuit, configured to convert an acoustic wave into an analog audio signal;

an analog-to-digital converter (ADC), coupled to the acoustic conversion circuit, configured to convert the analog audio signal into digital audio data; and

a controller comprising;

a first-level voice detection circuit, coupled to the acoustic conversion circuit, configured to detect voice activity in the analog audio signal;

a second-level voice detection circuit, coupled to the first-level voice detection circuit, configured to detect a beginning syllable of a key phrase in the digital audio data when the voice activity is detected; and

a third-level voice detection circuit, coupled to the second-level voice detection circuit, configured to detect the key phrase from the digital audio data only when the beginning syllable of the key phrase is detected in the digital audio data.

2. The audio device of claim 1, wherein when the key phrase is detected in the digital audio data, the third-level voice detection circuit is configured to transmit a wake-up signal to the host device, to wake up the host device from a sleep mode.

3. The audio device of claim 1, wherein the controller further comprises:

an audio analysis circuit, coupled to the third-level voice detection circuit, and when the key phrase is detected in the digital audio data, configured to generate configuration information of the acoustic conversion circuit based on the digital audio data, and transmit the configuration information to the host device.

4. The audio device of claim 3, wherein the configuration information of the acoustic conversion circuit comprises a transducer phase, a transducer sensitivity, a transducer noise floor, a transducer placement geometry, inter-transducer distances, and a transducer frequency response of the acoustic conversion circuit.

5. The audio device of claim 3, wherein when the key phrase is detected in the digital audio data, the audio analysis circuit is further configured to generate ambient acoustics information based on the digital audio data and transmit the ambient acoustics information to the host device;

and the ambient acoustics information comprises a classification and a feature extracted from the digital audio data.

6. The audio device of claim 1, wherein the controller further comprises:

a voice signal processing circuit, coupled to the third-level voice detection circuit, and when the key phrase is detected in the digital audio data, configured to performing voice signal enhancement on the digital audio data.

7. The audio device of claim 5, wherein the voice signal processing circuit is configured to compress the digital audio data and transmit the compressed digital audio data to the host device.

8. The audio device of claim 1, further comprises:

a voice data buffer, coupled to the ADC, configured to buffer the digital audio data from the ADC.

9. The audio device of claim 1, wherein the key phrase is user-defined.

10. A method, adopted by an audio device to detect a voice, wherein the audio device is coupled to a host device, the method comprising:

converting, by an acoustic conversion circuit, an acoustic wave into an analog audio signal;

converting, by an analog-to-digital converter (ADC), the analog audio signal into digital audio data; and

detecting, by a first-level voice detection circuit, voice activity in the analog audio signal;

detecting, by a second-level voice detection circuit, a beginning syllable of a key phrase in the digital audio data when the voice activity is detected in the digital audio data; and

detecting, by a third-level voice detection circuit, the key phrase from the digital audio data only when the beginning syllable of the key phrase is detected in the digital audio data.

11. The method of claim 10, further comprises:

when the key phrase is detected in the digital audio data, transmitting, by the third-level voice detection circuit, a wake-up signal to the host device, to wake up a host device from a sleep mode.

12. The method of claim 10, further comprising:

when the key phrase is detected in the digital audio data, generating, by an audio analysis circuit, configuration information of the acoustic conversion circuit based on the digital audio data, and transmitting the configuration information to the host device.

13. The method of claim 12, wherein the configuration information of the acoustic conversion circuit comprises a transducer phase, a transducer sensitivity, a transducer noise floor, a transducer placement geometry, inter-transducer distances, and a transducer frequency response of the acoustic conversion circuit.

14. The method of claim 12, further comprises:

when the key phrase is detected in the digital audio data, generating, by an audio analysis circuit, ambient acoustics information based on the digital audio data;

transmitting, by an audio analysis circuit, the ambient acoustics information to the host device;

wherein the ambient acoustics information comprises a classification and a feature extracted from the digital audio data.

15. The method of claim 10, further comprises:

when the key phrase is detected in the digital audio data, performing, by a voice signal processing circuit, voice signal enhancement on the digital audio data.

16. The method of claim 15, further comprises:

compressing, by the voice signal processing circuit, the digital audio data; and

transmitting, by the voice signal processing circuit, the compressed digital audio data to the host device.

17. The method of claim 10, further comprising:

buffering, by a voice data buffer, the digital audio data from the ADC.

18. The method of claim 10, wherein the key phrase is user-defined.