Devices and methods for identifying a prompt corresponding to a voice input in a sequence of prompts

• US 8,311,838 B2
• Filed: 01/13/2010
• Issued: 11/13/2012
• Est. Priority Date: 01/13/2010
• Status: Active Grant

• Current Assignee: Apple Inc.
• Original Assignee: Apple Inc.
• Inventors: Lindahl, Aram, Wood, Policarpo
• Primary Examiner(s): PULLIAS, JESSE SCOTT
• APPLICATION: US 20110172994A1
• Time in patent office: 1035 Days
• Field of Search: None
• US Class Current: 704/270.1
• CPC Class Codes: G06F 3/167 Audio in a user interface, e.g. using voice commands for navigating, audio feedback
• CPC Class Codes: G10L 15/22 Procedures used during a speech recognition process, e.g. man-machine dialogue
• CPC Class Codes: G10L 2015/228 of application context

Abstract

This is directed to processing voice inputs received by an electronic device while prompts are provided. In particular, this is directed to providing a sequence of prompts to a user (e.g., voice over prompts) while monitoring for a voice input. When the voice input is received, a characteristic time stamp can be identified for the voice input, and can be compared to periods or windows associated with each of the provided prompts. The electronic device can then determine that the prompt corresponding to a window that includes the characteristic time stamp was the prompt to which the user wished to apply the voice input. The device can process the voice input to extract a user instruction, and apply the instruction to the identified prompt (e.g., and perform an operation associated with the prompt).

Claims

1. A method for processing a voice input provided in response to a prompt, comprising:

at an electronic device with at least one processor and memory;

automatically providing a sequence of prompts, wherein each prompt is associated with a respective time period of a plurality of time periods;

receiving a voice input while a prompt of the sequence of prompts is being provided;

identifying a characteristic time associated with the received voice input;

identifying a time period of the plurality of time periods that includes the characteristic time; and

applying the received voice input to a respective prompt of the sequence of prompts associated with the identified time period.

2. The method of claim 1, further comprising:

defining, for each prompt, an initial time stamp and a final time stamp, wherein the period between the initial time stamp and the final time stamp constitutes the time period associated with the prompt.

3. The method of claim 2, wherein:

the initial time stamp is different from the time stamp corresponding to starting to provide the prompt; and

the final time stamp is different from the time stamp corresponding to stopping to provide the prompt.

4. The method of claim 3, wherein:

the final time stamp is after the time stamp corresponding to stopping to provide the prompt.

5. The method of claim 2, further comprising:

defining at least one of a final time stamp and an initial time stamp such that time periods associated with sequentially provided prompts overlap.

6. The method of claim 1, further comprising:

determining the relative importance of each prompt; and

varying the length of the time period of each prompt based on the determined relative importance of the prompt.

7. The method of claim 6, wherein varying further comprises:

varying the amount by which the final time stamp exceeds the time stamp corresponding to stopping to provide the prompt.

8. The method of claim 7, further comprising:

ordering the prompts such that a less important prompt is between more important prompts to prevent the time periods associated with the more important prompts from overlapping.

9. The method of claim 1, wherein identifying a characteristic time further comprises:

identifying a characteristic time stamp during which the voice input is received.

10. The method of claim 9, further comprising:

defining, for each prompt, an initial time stamp and a final time stamp, wherein the period between the initial time stamp and the final time stamp constitutes the time period associated with the prompt; and

identifying the combination of initial time stamp and final time stamp for which the characteristic time stamp is larger than the initial time stamp but smaller than the final time stamp.

11. The method of claim 1, wherein:

automatically providing a sequence of prompts further comprises automatically providing a sequence of voice output prompts, wherein each prompt is associated with a distinct electronic device operation.

12. The method of claim 1, wherein:

receiving the voice input while the respective prompt is being provided includes receiving the voice input while a visual prompt is being displayed, an audio prompt is being output, or a haptic prompt is being provided.

13. An electronic device for processing voice inputs, comprising:

an output interface for outputting a plurality of audio prompts, wherein the audio prompts are provided in succession;

an input interface for receiving a voice input; and

a processing module operative to;

determine that at least two audio prompts were output while the voice input was received;

define a characteristic time stamp for the voice input;

compare the characteristic time stamp with input windows associated with each of the at least two audio prompts, wherein each input window defines a duration during which received inputs correspond to the audio prompt of the input window; and

associate the received voice input with the audio prompt of the input window that includes the characteristic time stamp.

14. The electronic device of claim 13, wherein the processing module is further operative to:

determine that the characteristic time stamp is included in the input windows of the at least two audio prompts;

define an additional characteristic time stamp for the voice input; and

determine which of the input windows includes both the characteristic time stamp and the additional characteristic time stamp.

15. The electronic device of claim 13, wherein the processing module is further operative to:

extract an instruction from the voice input; and

apply the extracted instruction to the audio prompt of the input window that includes the characteristic time stamp.

16. The electronic device of claim 15, wherein the processing module is further operative to:

identify an operation associated with the, audio prompt of the input window that includes the characteristic time stamp;

determine the manner in which to perform the operation based on the received instruction; and

perform the operation in the determined manner.

17. The electronic device of claim 16, wherein the processing module is further operative to:

determine at least one variable characterizing the operation from the instruction; and

perform the operation using the at least one variable from the instruction.

18. A method for defining input windows to associate with provided prompts, comprising:

at an electronic device with at least one processor and memory;

identifying a plurality of prompts to provide in sequence, wherein each prompt is associated with a distinct electronic device operation;

defining an offset relative to at least one of a start time and an end time for providing each of the plurality of prompts; and

determining, for each of the plurality of prompts, an input window defined by an initial time and a final time for determining which provided prompt of the plurality of prompts to associate with a received voice input, wherein at least one of the initial time and the final time are offset from the start time and end time by the defined offset.

19. The method of claim 18, further comprising:

determining the importance of each prompt; and

varying the defined offset for each prompt based on the importance of the prompt.

20. The method of claim 18, further comprising:

defining a first offset to apply to the initial time relative to the start time; and

defining a second offset to apply to the final time relative to the end time, wherein the first and second offsets are different

21. The method of claim 18, wherein the offset is defined as at least one of:

a duration;

a percentage of the duration the prompt is provided; and

a percentage of the duration of another prompt provided in the sequence of plurality of prompts.

22. A non-transitory computer readable medium for processing a voice input provided in response to a prompt, the computer readable medium storing instructions for:

automatically providing a sequence of prompts, wherein each prompt is associated with a respective time period of a plurality of time periods;

receiving a voice input while a prompt of the sequence of prompts is being provided;

identifying a characteristic time associated with the received voice input;

identifying a time period of the plurality of time periods that includes the characteristic time; and

applying the received voice input to a respective prompt of the sequence of prompts associated with the identified time period.

23. The computer readable medium claim 22, further storing instructions for:

defining, for each prompt, an initial time stamp and a final time stamp, wherein the period between the initial time stamp and the final time stamp constitutes the time period associated with the prompt.

24. The computer readable medium claim 23, wherein:

the initial time stamp is different from the time stamp corresponding to starting to provide the prompt; and

the final time stamp is different from the time stamp corresponding to stopping to provide the prompt.

25. The computer readable medium of claim 22, wherein:

the instructions for receiving the voice input while the respective prompt is being provided include instructions for receiving the voice input while a visual prompt is being displayed, an audio prompt is being output, or a haptic prompt is being provided.