Method for detecting voice and electronic device using the same

• US 10,269,347 B2
• Filed: 02/03/2017
• Issued: 04/23/2019
• Est. Priority Date: 02/05/2016
• Status: Active Grant

• Current Assignee: Samsung Electronics Co. Ltd.
• Original Assignee: Samsung Electronics Co. Ltd.
• Inventors: Jang, Sungwoon, Shin, Sangwook, Youn, Sungwan
• Primary Examiner(s): Riley, Marcus T
• Application Number:
  US15/423,840
• Publication Number:
  US 20170229119A1
• Time in Patent Office: 809 Days
• Field of Search: None
• CPC Class Codes: G10L 15/08 Speech classification or search
• CPC Class Codes: G10L 15/22 Procedures used during a speech recognition process, e.g. man-machine dialogue
• CPC Class Codes: G10L 2015/088 Word spotting

Abstract

An electronic device is provided, which includes a housing; a microphone located on or within a predetermined distance of a first portion of the housing; a speaker located on or within a predetermined distance of a second portion of the housing; a communication circuit; a processor electrically connected to the microphone, the speaker, and the communication circuit; and a memory electrically connected to the processor configured to store a message to be provided as a voice through the speaker, wherein the memory stores instructions, wherein the processor is configured to execute the instructions to perform operations comprising: determining time information corresponding to a first part of the message if providing of the message is necessary, outputting the message through the speaker, receiving an input sound through the microphone while at least a part of the message is output, and processing the input sound using the time information to detect at least one word or sentence from the input sound, and the processing the input sound includes processing the input sound by ignoring at least a part of the input sound using the time information.

Claims

1. An electronic device comprising:

a housing;

a microphone disposed in or within a predetermined distance of a first portion of the housing;

a speaker disposed in or within a predetermined distance of a second portion of the housing;

a communication circuit;

a processor electrically connected to the microphone, the speaker, and the communication circuit; and

a memory electrically connected to the processor and wherein the memory is configured to store a message to be provided as a voice through the speaker,

wherein the processor is configured to execute instructions stored in the memory to perform operations comprising;

determining time information corresponding to a first part of the message if providing of the message is necessary,

outputting the message through the speaker,

receiving an input sound through the microphone while at least a part of the message is output, and

processing the input sound using the time information to detect at least one word or sentence from the input sound,

wherein processing the input sound includes ignoring at least a part of the input sound using the time information, and

wherein the time information comprises a reproduction time of the first part of the message.

2. The electronic device of claim 1, wherein the processing includes processing the input sound by ignoring at least the part of the input sound in a section that includes at least one of before or after preprocessing.

3. The electronic device of claim 2, wherein the processing includes processing the input sound by ignoring at least the part of the input sound using zero-padding before the preprocessing.

4. The electronic device of claim 1, wherein the processing includes processing the input sound by ignoring at least the part of the input sound in a section that includes at least one of before or after voice detection.

5. The electronic device of claim 4, wherein the processing includes processing the input sound by ignoring the word or sentence that corresponds to the time information after the voice detection.

6. The electronic device of claim 1, wherein the time information comprises at least one of:

a start time, an end time, or a duration time of the word or sentence.

7. A method for processing an input sound of an electronic device, comprising:

storing a message to be provided as a voice through a speaker;

determining time information corresponding to a first part of the message if providing of the message is necessary;

outputting the message through the speaker;

receiving an input sound through a microphone while at least a part of the message is output; and

processing the input sound using the time information in order to detect at least one word or sentence from the input sound,

wherein the processing the input sound includes processing the input sound by ignoring at least a part of the input sound using the time information, and

wherein the time information comprises a reproduction time of the first part of the message.

8. The method of claim 7, wherein the processing the input sound comprises processing the input sound by ignoring at least the part of the input sound in a section that includes at least one of before or after preprocessing.

9. The method of claim 8, wherein the processing the input sound comprises processing the input sound by ignoring at least the part of the input sound using zero-padding before the preprocessing.

10. The method of claim 7, wherein the processing the input sound comprises processing the input sound by ignoring at least the part of the input sound in a section that includes at least one of before or after voice detection.

11. The method of claim 10, wherein the processing the input sound comprises processing the input sound by ignoring the word or sentence that corresponds to the time information after the voice detection.

12. The method of claim 7, wherein the time information comprises at least one of:

a start time, an end time, or a duration time of the word or sentence.

13. An electronic device comprising:

an output disposed at one end of the electronic device;

an input disposed at another end of the electronic device;

a keyword detection module comprising keyword detection circuitry;

a processor electrically connected to the output, the input, and the keyword detection module; and

a memory electrically connected to the processor,

wherein the processor is configured to execute instructions stored in the memory to perform operations comprising;

analyzing a sound source that is reproduced at the output, and

limiting keyword detection at the input to correspond to the analysis,

wherein the analyzing includes analyzing a reproduction time of a keyword that is included in the sound source, and the limiting the keyword detection includes limiting the keyword detection at the input if the analyzed reproduction time of the keyword arrives.

14. The electronic device of claim 13, wherein analyzing the reproduction time of the keyword includes discriminating a changing phrase and a fixed phrase from a whole phrase of the sound source, and the operations further comprise:

determining a total reproduction time of the changing phrase,

determining the reproduction time of the keyword that is included in the fixed phrase, and

determining the reproduction time of the keyword within the whole phrase.

15. The electronic device of claim 13, wherein analyzing the sound source includes detecting the keyword that is included in the sound source, and

limiting the keyword detection includes limiting the keyword detection at the input if the keyword is detected at the output.

16. The electronic device of claim 13, wherein analyzing the sound source includes detecting the keyword that is included in the sound source, and the operations further comprise:

mixing a non-audible signal with the keyword at the output, and

limiting the keyword detection includes limiting the keyword detection at the input if the non-audible signal is sensed at the input end.

17. The electronic device of claim 13, wherein the operations further comprise determining whether speech is made, and

limiting the keyword detection includes limiting the keyword detection at the input through preprocessing if the sound source is not speech.

18. The electronic device of claim 13, wherein the operations further comprise:

setting preprocessing for reducing distortion of speech if the sound source is reproduced at the output during speech.

19. The electronic device of claim 13, wherein the operations further comprise:

setting preprocessing to not use acoustic echo cancelling circuitry so that speech has no distortion if the sound source is not reproduced at the output during speech.