Handsfree device with countinuous keyword recognition

• US 8,468,023 B1
• Filed: 10/01/2012
• Issued: 06/18/2013
• Est. Priority Date: 10/01/2012
• Status: Active Grant

• Current Assignee: Google LLC (Alphabet Inc.)
• Original Assignee: Google Inc. (Alphabet Inc.)
• Inventors: Stracke, John Richard Jr.
• Primary Examiner(s): Abebe, Daniel D
• Application Number:
  US13/632,723
• Time in Patent Office: 260 Days
• Field of Search: 704/270, 704/275, 455/569.1
• US Class Current: 704/275
• CPC Class Codes: G06F 3/167 Audio in a user interface, e.g. using voice commands for navigating, audio feedback
• CPC Class Codes: G10L 15/08 Speech classification or search
• CPC Class Codes: G10L 15/30 Distributed recognition, e.g. in client-server systems, for mobile phones or network applications
• CPC Class Codes: G10L 2015/088 Word spotting
• CPC Class Codes: H04M 1/6066 including a wireless connection
• CPC Class Codes: H04M 2250/02 including a Bluetooth interface
• CPC Class Codes: H04M 2250/74 with voice recognition means voice activated dialling H04M1/271; voice recognition algorithms G10L15/00
• CPC Class Codes: H04R 1/1091 Details not provided for in groups H04R1/1008 - H04R1/1083
• CPC Class Codes: H04R 2201/107 Monophonic and stereophonic headphones with microphone for two-way hands free communication
• CPC Class Codes: H04R 2201/109 Arrangements to adapt hands free headphones for use on both ears
• CPC Class Codes: H04R 2420/07 Applications of wireless loudspeakers or wireless microphones

Abstract

A handsfree device, which is coupled to a data processing device, may be operable to monitor at least one audio stream for occurrence of at least one keyword. Upon recognition of the at least one keyword, the handsfree device may establish a first connection between the handsfree device and the data processing device for launching a voice interface in the data processing device. The handsfree device may send audio data received after the recognition of the at least one keyword to the data processing device, via the first connection for responding to the audio data via the voice interface. During a keyword configuration operation, the handsfree device may send at least one inputted keyword to the data processing device for recording. The handsfree device may receive, via a second connection, the recorded at least one keyword from the data processing device for keyword configuration of the handsfree device.

Claims

1. A method, comprising:

in a handsfree device coupled to a data processing device;

monitoring at least one received audio stream for occurrence of at least one keyword, wherein the handsfree device has been configured, during a keyword configuration operation, to recognize the at least one keyword;

upon recognition of the at least one keyword, establishing a first connection between the handsfree device and the data processing device for launching a voice interface in the data processing device; and

sending audio data, which are received after the recognition of the at least one keyword, to the data processing device via the established first connection for responding to the sent audio data, by the data processing device, via the voice interface, wherein, during the keyword configuration operation, the handsfree device is operable to;

receive input of the at least one keyword;

send the inputted at least one keyword to the data processing device for recording, by the data processing device, of the inputted at least one keyword;

receive, via a second connection, the recorded at least one keyword from the data processing device; and

perform configuration of the handsfree device, utilizing the recorded at least one keyword, for recognizing the at least one keyword in the at least one received audio stream.

2. The method according to claim 1, comprising buffering the audio data to be sent to the data processing device during a time interval corresponding to establishing the first connection.

3. The method according to claim 1, comprising entering the keyword configuration operation when:

the data processing device receives a request for keyword configuration; and

the data processing device causes the handsfree device to enter the keyword configuration operation based on the received request.

4. The method according to claim 1, comprising entering the keyword configuration operation when:

the handsfree device is first coupled to the data processing device;

the data processing device discovers that the handsfree device is capable of monitoring the at least one received audio stream for occurrence of the at least one keyword;

the data processing device determines that the handsfree device has not been configured to recognize the at least one keyword; and

the data processing device causes the handsfree device to enter the keyword configuration operation by prompting and requesting input of the at least one keyword, via the handsfree device.

5. The method according to claim 4, wherein, when the data processing device determines that the handsfree device has been configured to recognize the at least one keyword, the data processing device enables a keyword configuration interface to allow recording of the at least one keyword via the keyword configuration operation, without requesting the input of the at least one keyword via the handsfree device.

6. The method according to claim 1, wherein the data processing device stores the recorded at least one keyword to allow reuse of the stored at least one keyword in a subsequent keyword configuration operation.

7. The method according to claim 1, wherein:

before sending the recorded at least one keyword to the handsfree device via the second connection for keyword configuration, the data processing device replays the recorded at least one keyword for review; and

as a result of the review of the recorded at least one keyword, the data processing device receives an indication, where the indication comprises acceptance of the recorded at least one keyword, rejection of the recorded at least one keyword, or cancellation of the keyword configuration operation.

8. A method, comprising:

in a handsfree device coupled to a data processing device;

monitoring at least one received audio stream for occurrence of at least one keyword, wherein the handsfree device has been configured, during a keyword configuration operation, to recognize the at least one keyword;

upon recognition of the at least one keyword, establishing a first connection between the handsfree device and the data processing device for launching a voice interface in the data processing device; and

sending audio data, which are received after the recognition of the at least one keyword, to the data processing device via the established first connection for responding to the sent audio data, by the data processing device, via the voice interface, wherein the handsfree device comprises the at least one keyword which is hard-coded into the handsfree device in a factory environment.

9. The method according to claim 8, wherein:

the handsfree device comprises at least one accent version of each of the at least one keyword, where the at least one accent version of each of the at least one keyword is hard-coded into the handsfree device in the factory environment; and

during the keyword configuration operation, at least one new keyword is allowed to be chosen from among the at least one accent version of each of the at least one keyword.

10. The method according to claim 8, wherein:

the handsfree device comprises at least one version of each of the at least one keyword, where the at least one version of each of the at least one keyword is hard-coded into the handsfree device in the factory environment, and the at least one version corresponds to at least one device type of the data processing device respectively; and

during the keyword configuration operation, at least one new keyword is allowed to be chosen from among the at least one version of each of the at least one keyword.

11. A system, comprising:

a handsfree device coupled to a data processing device, the handsfree device being operable to;

monitor at least one received audio stream for occurrence of at least one keyword, wherein the handsfree device has been configured, during a keyword configuration operation, to recognize the at least one keyword;

upon recognition of the at least one keyword, establish a first connection between the handsfree device and the data processing device for launching a voice interface in the data processing device; and

send audio data, which are received after the recognition of the at least one keyword, to the data processing device via the established first connection for responding to the sent audio data, by the data processing device, via the voice interface, wherein, during the keyword configuration operation, the handsfree device is operable to;

receive input of the at least one keyword;

send the inputted at least one keyword to the data processing device for recording, by the data processing device, of the inputted at least one keyword;

receive, via a second connection, the recorded at least one keyword from the data processing device; and

perform configuration of the handsfree device, utilizing the recorded at least one keyword, for recognizing the at least one keyword in the at least one received audio stream.

12. The system according to claim 11, wherein the handsfree device is operable to enter the keyword configuration operation when:

the data processing device receives a request for keyword configuration; and

the data processing device causes the handsfree device to enter the keyword configuration operation based on the received request.

13. The system according to claim 11, wherein the handsfree device is operable to enter the keyword configuration operation when:

the handsfree device is first coupled to the data processing device;

the data processing device discovers that the handsfree device is capable of monitoring the at least one received audio stream for occurrence of the at least one keyword;

the data processing device determines that the handsfree device has not been configured to recognize the at least one keyword; and

the data processing device causes the handsfree device to enter the keyword configuration operation by prompting and requesting input of the at least one keyword via the handsfree device.

14. The system according to claim 13, wherein, when the data processing device determines that the handsfree device has been configured to recognize the at least one keyword, the data processing device enables a keyword configuration interface to allow recording of the at least one keyword via the keyword configuration operation, without requesting the input of the at least one keyword via the handsfree device.

15. A method, comprising:

in a Bluetooth handsfree device coupled to a data processing device via Bluetooth communication;

monitoring at least one received audio stream for occurrence of at least one keyword, wherein the Bluetooth handsfree device has been configured, during a keyword configuration operation, to recognize the at least one keyword;

upon recognition of the at least one keyword, establishing a first connection between the Bluetooth handsfree device and the data processing device for launching a voice interface in the data processing device; and

sending audio data, which are received after the recognition of the at least one keyword, to the data processing device via the established first connection for responding to the sent audio data, by the data processing device, via the voice interface, wherein, during the keyword configuration operation, the Bluetooth handsfree device is operable to;

receive input of the at least one keyword;

send the inputted at least one keyword to the data processing device for recording, by the data processing device, of the inputted at least one keyword;

receive, via a second connection, the recorded at least one keyword from the data processing device; and

perform configuration of the Bluetooth handsfree device, utilizing the recorded at least one keyword, for recognizing the at least one keyword in the at least one received audio stream.

16. The method according to claim 15, comprising entering the keyword configuration operation when:

the Bluetooth handsfree device is first coupled to the data processing device;

the data processing device discovers that the Bluetooth handsfree device is capable of monitoring the at least one received audio stream for occurrence of the at least one keyword;

the data processing device determines that the Bluetooth handsfree device has not been configured to recognize the at least one keyword; and

the data processing device causes the Bluetooth handsfree device to enter the keyword configuration operation by prompting and requesting input of the at least one keyword via the Bluetooth handsfree device.

17. The method according to claim 16, wherein the data processing device utilizes a Bluetooth service discovery protocol (SDP) to discover that the Bluetooth handsfree device is capable of monitoring the at least one received audio stream for occurrence of the at least one keyword.