Method of voice recognition and electronic apparatus

• US 10,068,570 B2
• Filed: 12/10/2013
• Issued: 09/04/2018
• Est. Priority Date: 12/10/2012
• Status: Active Grant

• Current Assignee: Lenovo (Beijing) Limited (Lenovo Group Ltd.), Lenovo Company Limited (Lenovo Group Ltd.)
• Original Assignee: Lenovo (Beijing) Limited (Lenovo Group Ltd.), Lenovo Company Limited (Lenovo Group Ltd.)
• Inventors: Dai, Haisheng, Wang, Qianying, Wang, Hao
• Primary Examiner(s): Dorvil, Richemond
• Assistant Examiner(s): Le, Thuykhanh
• Application Number:
  US14/101,961
• Publication Number:
  US 20140163984A1
• Time in Patent Office: 1,729 Days
• Field of Search: None
• CPC Class Codes: G10L 15/04 Segmentation; Word boundary detection
• 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 25/87 Detection of discrete points within a voice signal

Abstract

A method of voice recognition and an electronic apparatus are described with the method of voice recognition being applied in an electronic apparatus. The method includes taking i=1 and detecting corresponding i-th voice sub-information at a moment Ti when the electronic apparatus detects that a user starts to talk at a moment T0, wherein the i-th voice sub-information voice information from the moment T0 to the moment Ti, the i-th voice sub-information is partial voice information of voice information with integral semantic corresponding to a moment Tj after the moment T0 to the moment Ti, and i is an integer greater than or equal to 1; and analyzing the i-th voice sub-information to obtain M results of analysis, M being an integer greater than or equal to 1.

Claims

1. A method of voice recognition applied in an electronic apparatus comprising:

when the electronic apparatus detects that a user starts to speak at a first moment, detecting by a microphone, a first voice sub-information at a second moment while a same user is speaking until a third moment, wherein the first voice sub-information includes voice information from the first moment to the second moment spoken by the same user, the first voice sub-information is partial voice information of voice information with integral semantic from the first moment to the third moment spoken by the same user, and

analyzing by a processor of the electronic apparatus the first voice sub-information to obtain a plurality of results of analysis while the same user is speaking,

displaying a part or all of the plurality of results of analysis on a display interface to receive a selection instruction of the user; and

deciding whether there is a first control instruction for stopping detecting whether the user is speaking;

detecting, by the microphone, a second voice sub-information at a fourth moment after the second moment when there is no first control instruction, wherein the second voice sub-information includes voice information from the first moment to the fourth moment spoken by the same user; and

analyzing, by the processor of the electronic apparatus, the second voice sub-information to obtain a plurality of results of analysis while the same user is speaking, the second voice sub-information comprising the first voice sub-information.

2. The method according to claim 1, wherein analyzing the first voice sub-information to obtain the plurality of results of analysis comprises analyzing the first voice sub-information to obtain a plurality of keyword text information, the plurality of keyword text information being exactly the plurality of results of analysis.

3. The method according to claim 1, wherein analyzing the first voice sub-information to obtain the plurality of results of analysis comprises:

analyzing the first voice sub-information to obtain a second plurality of keyword text information, and

obtaining the plurality of results of matching whose match degree with any of the second plurality of keyword text information is larger than a first preset threshold based on the second plurality of keyword text information, the plurality of results of matching being exactly the plurality of results of analysis.

4. The method according to claim 1, wherein after analyzing the first voice sub-information to obtain the plurality of results of analysis, the method further comprises:

stopping detecting whether the user is speaking when there is the first control instruction.

5. The method according to claim 4, wherein deciding whether there is the first control instruction for stopping detecting whether the user is speaking further comprises deciding whether there is a selection operation of selecting a first result of analysis in a third plurality of results of analysis to obtain a decision result, wherein when the result of decision indicates that there is the selection operation, the first control instruction is generated.

6. The method according to claim 5, wherein the selection operation comprises an operation carried out through a first input mode, the first input mode being an input mode different from a voice input mode.

7. The method according to claim 5, wherein before displaying the third plurality of results of analysis in the plurality of results of analysis on the display interface, the method further comprises:

scoring the plurality of results of analysis according to the match degree to obtain a plurality of first point value;

or

scoring the plurality of results of analysis according to the historical selection information to obtain a plurality of second point values;

or

scoring the plurality of results of analysis according to the match degree and the historical selection information to obtain a plurality of third point values.

8. The method according to claim 7, wherein before displaying the second plurality of results of analysis in the plurality of results of analysis on the display interface, the method further comprises:

acquiring the second plurality of results of analysis having the highest point value among the first point values, the second point values or the third point values from the plurality of results of analysis; and

displaying the second plurality of results of analysis on the display interface.

9. The method according to claim 1, wherein analyzing the first voice sub-information to obtain the plurality of results of analysis comprises carrying out voiceprint analysis to the first voice sub-information to obtain the plurality of results of analysis.

10. An electronic apparatus comprising:

a detecting chip for when the electronic apparatus detects that a user starts to speak at a first moment, detecting a first voice sub-information at a second moment by a microphone while the same user is speaking until a third moment, wherein the first voice sub-information includes voice information from the first moment to the second moment spoken by the same user, the first voice sub-information is partial voice information of voice information with integral semantic from the first moment to the third moment spoken by the same user

an analyzing chip for analyzing the first voice sub-information to obtain a plurality of results of analysis while the same user is speaking

a displaying chip for displaying a part or all of the plurality of results of analysis on a display interface to receive a selection instruction of the user; and

a deciding chip for deciding whether there is a first control instruction for stopping detecting whether the user is speaking;

wherein the detecting chip detecting a second voice sub-information at a fourth moment after the second moment when there is no first control instruction, wherein the second voice sub-information includes voice information from the first moment to the fourth moment spoken by the same user; and

the analyzing chip analyzing the second voice sub-information to obtain a plurality of results of analysis while the same user is speaking, the second voice sub-information comprising the first voice sub-information.

11. The electronic apparatus according to claim 10, wherein the analyzing chip comprises analyzing the first voice sub-information to obtain a plurality of keyword text information, the plurality of keyword text information being exactly the plurality of results of analysis.

12. The electronic apparatus according to claim 10, wherein the analyzing chip comprises:

an analyzing sub-chip for analyzing the first voice sub-information to obtain a second plurality of keyword text information; and

a matching sub-chip for obtaining the plurality of results of matching whose match degree with any of the second plurality of keyword text information is larger than a first preset threshold based on the second plurality of keyword text information, the plurality of results of matching being exactly the plurality of results of analysis.

13. The electronic apparatus according to claim 10, wherein the electronic apparatus further comprises:

a stopping chip for stopping detecting whether the user is speaking when there is the first control instruction.

14. The electronic apparatus according to claim 13, wherein the deciding chip comprises:

a deciding sub-chip for deciding whether there is a selection operation of selecting a first result of analysis in a second plurality of results of analysis to obtain a result of decision; and

a generating sub-chip for generating the first control instruction when the result of decision indicates that there is the selection operation.

15. The electronic apparatus according to claim 14, wherein the selection operation includes an operation carried out through a first input mode, the first input mode being an input mode different from a voice input mode.

16. The electronic apparatus according to claim 10, wherein the electronic apparatus further comprises:

a scoring chip for scoring the plurality of results of analysis according to match degree to obtain a plurality of first point values before displaying the second plurality of results of analysis in the plurality of results of analysis on the display interface;

or

scoring the plurality of results of analysis according to historical selection information to obtain a plurality of second point values;

or

scoring the plurality of results of analysis according to the match degree and historical selection information to obtain a plurality of third point values.

17. The electronic apparatus according to claim 16, wherein the display chip comprises:

an acquiring sub-chip for acquiring the plurality of results of analysis having the highest point value among the first point values, the second point values or the third point values from the plurality of results of analysis; and

a displaying sub-chip for displaying the second plurality of results of analysis on the display interface.

18. The electronic apparatus according to claim 10, wherein the analyzing chip comprises carrying out voiceprint analysis to the first voice sub-information to obtain the plurality of results of analysis.