Wearable computer system and modes of operating the system

• US 7,562,020 B2
• Filed: 03/03/2006
• Issued: 07/14/2009
• Est. Priority Date: 02/28/2002
• Status: Expired due to Term

• Current Assignee: Accenture Global Services Limited (Accenture PLC)
• Original Assignee: Accenture Global Services GmbH (Accenture PLC)
• Inventors: Richter, Owen E., Le, Dana, Hughes, Lucian P.
• Primary Examiner(s): Patel; Paresh
• Assistant Examiner(s): Kusumakar; Karen M
• Application Number:
  US11/367,732
• Publication Number:
  US 20060187628A1
• Time in Patent Office: 1,229 Days
• Field of Search: 381/41, 381/43, 381/47, 381/51, 381/68, 381/68.2, 381/68.4, 381/68.6, 348/158, 348/373, 348/376, 345/7, 364/513, 707/3, 361/679, 361/683, 704/200, 704/243, 704/257, 704/270, 704/275
• US Class Current: 704/275
• CPC Class Codes: G06F 1/163 Wearable computers, e.g. on a belt
• CPC Class Codes: G06F 3/16 Sound input; Sound output speech processing G10L
• CPC Class Codes: H04M 1/05 specially adapted for use on head, throat or breast
• CPC Class Codes: H04M 1/6058 involving the use of a headset accessory device connected to the portable telephone

Abstract

A wearable computer system has a user interface with at least an audio-only mode of operating, and that is natural in appearance and facilitates natural interactions with the system and the user'"'"'s surroundings. The wearable computer system may retrieve information from the user'"'"'s voice or surroundings using a passive user interface. The audio-only user interface for the wearable computer system may include two audio receivers and a single output device, such as a speaker, that provides audio data directly to the user. The two audio receivers may be miniature microphones that collaborate to input audio signals from the user'"'"'s surroundings while also accurately inputting voice commands from the user. Additionally, the user may enter natural voice commands to the wearable computer system in a manner that blends in with the natural phrases and terminology spoken by the user.

Claims

1. A method implemented by a wearable computer device, comprising:

continuously recording a conversation in a scrolling memory buffer that stores audio data for a predetermined period of time, and that discards the audio data after the predetermined period of time has expired if a user has not issued a voice command to move the audio data to a separate memory for output at a later time;

accessing voice commands stored in the separate memory, the voice commands for storing audio data surrounding a receipt of a respective voice command in the separate memory, each voice command being customized by the user to blend with natural conversational phrasing and terminology without disrupting the conversation, and each voice command specifying;

an amount of audio data stored in the scrolling memory buffer before receipt of the respective voice command to move into the separate memory upon receipt of the respective voice command, the amount of audio data to move being less than all of the audio data stored in the scrolling memory buffer, and

an amount of audio data to record in the separate memory after receipt of the respective voice commands;

recognizing, using a processor, phrases spoken by the user during the conversation;

determining, using the processor, that a recognized phrase spoken by the user during the conversation matches an accessed voice command;

moving the amount of audio data specified by the accessed voice command from the scrolling memory to the separate memory, and recording the amount of audio data specified by the accessed voice command in the separate memory, based on determining that the recognized phrase spoken by the user during the conversation matches the accessed voice command; and

at the later time, outputting the audio data surrounding the receipt of the accessed voice command, using an earpiece of the wearable computer device.

2. The method of claim 1, further comprising:

storing a current location, current time and current date in the separate memory when determining that the recognized phrase spoken by the user during the conversation matches the accessed voice command.

3. The method of claim 2, further comprising determining the current location using an infrared (IR) beacon.

4. The method of claim 1, further comprising uploading the audio data surrounding the receipt of the accessed voice command to a remote computing device for later output.

5. The method of claim 1, further comprising:

capturing a camera image, using a camera of the wearable computer device, when determining that the recognized phrase spoken by the user during the conversation matches the accessed voice command.

6. The method of claim 1, further comprising, during a voice command set-up procedure:

prompting the user to specify, via spoken input;

a phrase that will serve as a new voice command,

the amount of audio data stored in the scrolling memory buffer before receipt of the new voice command to move into the separate memory upon receipt of the new voice command, and

the amount of audio data to record in the separate memory after receipt of the new voice command; and

recognizing the spoken input of the user in response to the prompting; and

adding the new voice command to the voice commands.

7. The method of claim 1, wherein the audio data surrounding the receipt of the accessed voice command is automatically output based on determining that the user has arrived at a specified location.

8. A wearable computer device, comprising:

a scrolling memory buffer configured to continuously record a conversation, the scrolling memory buffer storing audio data for a predetermined period of time, and discarding the audio data after the predetermined period of time has expired if a user has not issued a voice command to move the audio data to a separate memory for output at a later time;

a separate memory storing voice commands, the voice commands for storing audio data surrounding a receipt of a respective voice command in the separate memory, each voice command being customized by the user to blend with natural conversational phrasing and terminology without disrupting the conversation, and each voice command specifying;

an amount of audio data stored in the scrolling memory buffer before receipt of the respective voice command to move into the separate memory upon receipt of the respective voice command, the amount of audio data to move being less than all of the audio data stored in the scrolling memory buffer, and

an amount of audio data to record in the separate memory after receipt of the respective voice commands,

a processor configured to;

recognize phrases spoken by the user during the conversation,

determine that a recognized phrase spoken by the user during the conversation matches a voice command, and

move the amount of audio data specified by the voice command from the scrolling memory to the separate memory, and record the amount of audio data specified by the voice command in the separate memory, based on determining that the recognized phrase spoken by the user during the conversation matches the voice command; and

an earpiece configured to, at the later time, output the audio data surrounding the receipt of the voice command.

9. The device of claim 8, wherein the separate memory is further configured to store a current location, current time and current date in the separate memory when determining that the recognized phrase spoken by the user during the conversation matches the accessed voice command.

10. The device of claim 9, further comprising an location determination module configured to determine the current location using an infrared (IR) beacon.

11. The device of claim 8, further comprising an interface configured to upload the audio data surrounding the receipt of the accessed voice command to a remote computing device for later output.

12. The device of claim 8, further comprising a camera configured to capture a camera image when determining that the recognized phrase spoken by the user during the conversation matches the accessed voice command.

13. The device of claim 8, further comprising a voice recognition engine configured to, during a voice command set-up procedure:

prompt the user to specify, via spoken input;

a phrase that will serve as a new voice command,

the amount of audio data stored in the scrolling memory buffer before receipt of the new voice command to move into the separate memory upon receipt of the new voice command, and

the amount of audio data to record in the separate memory after receipt of the new voice command; and

recognize the spoken input of the user in response to the prompting; and

add the new voice command to the voice commands.

14. The device of claim 8, wherein the audio data surrounding the receipt of the accessed voice command is automatically output based on determining that the user has arrived at a specified location.

15. A computer-readable medium encoded with a computer program comprising instructions that, when executed, operate to cause a computer to perform operations comprising:

continuously recording a conversation in a scrolling memory buffer that stores audio data for a predetermined period of time, and that discards the audio data after the predetermined period of time has expired if a user has not issued a voice command to move the audio data to a separate memory for output at a later time;

accessing voice commands stored in the separate memory, the voice commands for storing audio data surrounding a receipt of a respective voice command in the separate memory, each voice command being customized by the user to blend with natural conversational phrasing and terminology without disrupting the conversation, and each voice command specifying;

an amount of audio data stored in the scrolling memory buffer before receipt of the respective voice command to move into the separate memory upon receipt of the respective voice command, the amount of audio data to move being less than all of the audio data stored in the scrolling memory buffer, and

an amount of audio data to record in the separate memory after receipt of the respective voice commands;

recognizing, using a processor, phrases spoken by the user during the conversation;

determining, using the processor, that a recognized phrase spoken by the user during the conversation matches an accessed voice command;

moving the amount of audio data specified by the accessed voice command from the scrolling memory to the separate memory, and recording the amount of audio data specified by the accessed voice command in the separate memory, based on determining that the recognized phrase spoken by the user during the conversation matches the accessed voice command; and

at the later time, outputting the audio data surrounding the receipt of the accessed voice command, using an earpiece of the wearable computer device.

16. The computer-readable medium of claim 15, wherein the operations further comprise:

storing a current location, current time and current date in the separate memory when determining that the recognized phrase spoken by the user during the conversation matches the accessed voice command.

17. The computer-readable medium of claim 16, wherein the operations further comprise determining the current location using an infrared (IR) beacon.

18. The computer-readable medium of claim 15, wherein the operations further comprise uploading the audio data surrounding the receipt of the accessed voice command to a remote computing device for later output.

19. The computer-readable medium of claim 15, wherein the operations further comprise:

capturing a camera image, using a camera of the wearable computer device, when determining that the recognized phrase spoken by the user during the conversation matches the accessed voice command.

20. The computer-readable medium of claim 15, wherein the operations further comprise, during a voice command set-up procedure:

prompting the user to specify, via spoken input;

a phrase that will serve as a new voice command,

the amount of audio data stored in the scrolling memory buffer before receipt of the new voice command to move into the separate memory upon receipt of the new voice command, and

the amount of audio data to record in the separate memory after receipt of the new voice command; and

recognizing the spoken input of the user in response to the prompting; and

adding the new voice command to the voice commands.