Method and device for voice controlling

• US 9,236,048 B2
• Filed: 01/12/2011
• Issued: 01/12/2016
• Est. Priority Date: 04/27/2010
• Status: Active Grant

• Current Assignee: Xi'An Zhongxing New Software Co., Ltd. (ZTE Corporation)
• Original Assignee: ZTE Corporation
• Inventors: Li, Manhai, Xiao, Kaili, Wang, Jingping, Liao, Xin
• Primary Examiner(s): Serrou, Abdelali
• Application Number:
  US13/575,717
• Publication Number:
  US 20130289995A1
• Time in Patent Office: 1,826 Days
• US Class Current: 1/1
• CPC Class Codes: G10L 15/04 Segmentation; Word boundary detection
• CPC Class Codes: G10L 15/18 using natural language modelling
• CPC Class Codes: G10L 15/22 Procedures used during a speech recognition process, e.g. man-machine dialogue
• CPC Class Codes: G10L 2015/221 Announcement of recognition results
• CPC Class Codes: G10L 2015/223 Execution procedure of a spoken command
• CPC Class Codes: G10L 2015/228 of application context
• CPC Class Codes: H04M 2250/74 with voice recognition means voice activated dialling H04M1/271; voice recognition algorithms G10L15/00

Abstract

The present invention discloses a method and device for voice control, which are used to solve the problem of low success rate of voice control in the prior art. The method includes: classifying stored recognition information used for voice recognizing to obtain a syntax packet corresponding to each type of recognition information (10); receiving an inputted voice signal, and performing a voice recognition processing respectively on the received voice signal by using each obtained syntax packet in turn (20), and performing a corresponding control processing based on a voice recognition result of the voice signal according to each syntax packet (30).

Claims

1. A method for voice control, comprising the following steps:

classifying stored recognition information used for voice recognition to obtain a plurality of syntax packets, wherein each syntax packet corresponds to one type of recognition information;

receiving an inputted voice signal, and performing a voice recognition processing repeatedly on the received voice signal by using each of the plurality of syntax packets in turn to obtain a plurality of voice data portions, each of which is recognized from the corresponding syntax packet, of the voice signal as a plurality of voice recognition results, wherein the plurality of voice recognition results include some voice data portions recognized successfully and/or voice recognition failure;

wherein, the step of performing a voice recognition processing repeatedly on the received voice signal by using each of the plurality of syntax packets comprises;

when at least one piece of recognition information in one of the syntax packets can be recognized from the received voice signal, selecting an identifier corresponding to the recognized piece of the recognition information from pre-designated identifiers corresponding to various pieces of the recognition information in the syntax packet as the voice recognition result of the syntax packet on the voice signal;

otherwise, determining that voice recognition fails this time, and selecting an identifier corresponding to a reason for voice recognition processing failure of this time from pre-designated identifiers corresponding to various reasons for voice recognition processing failure as the voice recognition result of the syntax packet on the voice signal; and

performing a corresponding control processing based on a combination of the plurality of voice recognition results as follows;

combining the voice recognition results of various syntax packets on the voice signal in a predetermined combining order, and sending a combination result to an external equipment;

receiving a query request sent from the external equipment, wherein the query request contains a splitting result obtained after the external equipment splits the combination result in a splitting order corresponding to the predetermined combining order;

selecting recognition information corresponding to the splitting result contained in the query request from a pre-designated corresponding relationship between the recognition information and the identifiers; and

providing the recognition information corresponding to the splitting result to the external equipment, so that the external equipment performs the control processing according to the recognition information corresponding to the splitting result.

2. The method according to claim 1, wherein, the step of performing a corresponding control processing based on a combination of the plurality of voice recognition results comprises:

when there is at least one identifier corresponding to the reason for voice recognition processing failure in the voice recognition results of various syntax packets on the voice signal, outputting a prompt signal for prompting voice recognition failure.

3. The method according to claim 1, wherein, the step of performing a corresponding control processing based on a combination of the plurality of voice recognition results comprises:

counting the number of identifiers corresponding to same reasons for voice recognition processing failure in the voice recognition results of various syntax packets on the voice signal, and prompting a user through a prompt message of a reason for voice recognition processing failure corresponding to the identifier with the largest number.

4. The method according to claim 1, wherein, the step of performing a corresponding control processing based on a combination of the plurality of voice recognition results comprises:

when there is no identifier corresponding to the reason for voice recognition processing failure in the voice recognition results of the designated syntax packets on the voice signal, performing a predetermined control processing corresponding to the voice recognition results of the designated syntax packets on the voice signal according to the voice recognition results of the designated syntax packets on the voice signal.

5. The method according to claim 1, wherein, the recognition information used for voice recognition comprises information of contact name type, information of contact way type and information of operation type.

9. The method according to claim 1, wherein, the recognition information used for voice recognition comprises information of contact name type, information of contact way type and information of operation type.

10. The method according to claim 2, wherein, the recognition information used for voice recognition comprises information of contact name type, information of contact way type and information of operation type.

11. The method according to claim 3, wherein, the recognition information used for voice recognition comprises information of contact name type, information of contact way type and information of operation type.

12. The method according to claim 4, wherein, the recognition information used for voice recognition comprises information of contact name type, information of contact way type and information of operation type.

13. The method according to claim 1, wherein, the recognition information used for voice recognition comprises information of contact name type, information of contact way type and information of operation type.

6. A device for voice control, comprising:

a syntax packet obtaining unit, which is used to classify stored recognition information used for voice recognition to obtain a plurality of syntax packets, wherein each syntax packet corresponds to one type of recognition information;

a voice recognition processing unit, which is used to receive an inputted voice signal, and perform a voice recognition processing repeatedly on the received voice signal by using each of the plurality of syntax packets in turn to obtain a plurality of voice data portions, each of which is recognized from the corresponding syntax packet, of the voice signal as a plurality of voice recognition results, wherein the plurality of voice recognition results include some voice data portions recognized successfully and/or voice recognition failure;

wherein, the voice recognition processing unit is used to perform a voice recognition processing repeatedly on the received voice signal by using each of the plurality of syntax packets as follows;

when at least one piece of recognition information in one of the syntax packets can be recognized from the received voice signal, selecting an identifier corresponding to the recognized piece of the recognition information from pre-designated identifiers corresponding to various pieces of the recognition information in the syntax packet as the voice recognition result of the syntax packet on the voice signal;

otherwise, determining that voice recognition fails this time, and selecting an identifier corresponding to a reason for voice recognition processing failure of this time from pre-designated identifiers corresponding to various reasons for voice recognition processing failure as the voice recognition result of the syntax packet on the voice signal;

a performing unit, which is used to perform a corresponding control processing based on a combination of the plurality of voice recognition results as follows;

combining the voice recognition results of various syntax packets on the voice signal in a predetermined combining order, and sending a combination result to an external equipment;

receiving a query request sent from the external equipment, wherein the query request contains a splitting result obtained after the external equipment splits the combination result in a splitting order corresponding to the predetermined combining order;

selecting recognition information corresponding to the splitting result contained in the query request from a pre-designated corresponding relationship between the recognition information and the identifiers; and

providing the recognition information corresponding to the splitting result to the external equipment, so that the external equipment performs the control processing according to the recognition information corresponding to the splitting result.

7. The device according to claim 6, wherein, the voice recognition processing unit specifically comprises a first determining sub-unit and a second determining sub-unit;

wherein, for each syntax packet obtained by the syntax packet obtaining unit,

the first determining sub-unit is used to, when at least one piece of recognition information in the syntax packet can be recognized from the received voice signal, select an identifier corresponding to the recognized piece of the recognition information from pre-designated identifiers corresponding to various pieces of the recognition information in the syntax packet as the voice recognition result of the syntax packet on the voice signal;

the second determining sub-unit is used to, when no recognition information in the syntax packet can be recognized from the received voice signal, determine that voice recognition fails this time, and select an identifier corresponding to a reason for voice recognition processing failure this time from pre-designated identifiers corresponding to various reasons for voice recognition processing failure as the voice recognition result of the syntax packet on the voice signal.

8. A device for voice control connected with an external equipment, comprising:

a syntax packet obtaining unit, which is used to classify stored recognition information used for voice recognition to obtain a plurality of syntax packets, wherein each syntax packet corresponds to one type of recognition information;

a voice recognition processing unit, which is used to receive an inputted voice signal, and perform a voice recognition processing repeatedly on the received voice signal by using each of the plurality of syntax packets obtained by the syntax packet obtaining unit in turn to obtain a plurality of voice data portions, each of which is recognized from the corresponding syntax packet, of the voice signal as a plurality of voice recognition results, wherein the plurality of voice recognition results include some voice data portions recognized successfully and/or voice recognition failure;

wherein, the voice recognition processing unit is used to perform a voice recognition processing repeatedly on the received voice signal by using each of the plurality of syntax packets as follows;

when at least one piece of recognition information in one of the syntax packets can be recognized from the received voice signal, selecting an identifier corresponding to the recognized piece of the recognition information from pre-designated identifiers corresponding to various pieces of the recognition information in the syntax packet as the voice recognition result of the syntax packet on the voice signal;

otherwise, determining that voice recognition fails this time, and selecting an identifier corresponding to a reason for voice recognition processing failure of this time from pre-designated identifiers corresponding to various reasons for voice recognition processing failure as the voice recognition result of the syntax packet on the voice signal;

a combining sub-unit, which is used to combine the voice recognition results of various syntax packets obtained by the voice recognition processing unit on the voice signal in a predetermined combining order, and send a combination result to the external equipment;

a receiving sub-unit, which is used to receive a query request sent from the external equipment, wherein the query request contains a splitting result obtained after the external equipment splits the combination result in a splitting order corresponding to the predetermined combining order;

a selecting sub-unit, which is used to select recognition information corresponding to the splitting result contained in the query request received by the receiving sub-unit from a pre-designated corresponding relationship between the recognition information and identifiers; and

a sending sub-unit, which is used to provide the recognition information corresponding to the splitting result selected by the selecting sub-unit to the external equipment, so that the external equipment performs the control processing according to the recognition information corresponding to the splitting result.