Method and apparatus for performing and controlling speech recognition and enrollment

• US 8,909,533 B2
• Filed: 12/09/2011
• Issued: 12/09/2014
• Est. Priority Date: 06/12/2009
• Status: Active Grant

• Current Assignee: Huawei Technologies Co., Ltd. (Huawei Investment & Holding Co., Ltd.)
• Original Assignee: Huawei Technologies Co., Ltd. (Huawei Investment & Holding Co., Ltd.)
• Inventors: Zhu, Ning, Yang, Weiwei
• Primary Examiner(s): Shah, Paras D
• Assistant Examiner(s): Sharma, Neeraj
• Application Number:
  US13/315,966
• Publication Number:
  US 20120078637A1
• Time in Patent Office: 1,096 Days
• Field of Search: 704/270, 704/275, 704/257, 704/273, 704/270.1, 704/10, 704/254, 704/235, 704/241, 713/156, 713/186, 709/224, 379/265.02, 379/88.17, 379/88.01, 379/88.22, 726/12
• US Class Current: 704/270.1
• CPC Class Codes: G10L 15/063 Training
• CPC Class Codes: H04L 65/1026 at the edge
• CPC Class Codes: H04L 65/103 in the network
• CPC Class Codes: H04L 65/1043 Gateway controllers, e.g. media gateway control protocol [MGCP] controllers

Abstract

A method and an apparatus for performing and controlling speech recognition and enrolment are provided. The method for performing speech recognition and enrolment includes: receiving a Speech Enrolment Start Request and a Speech Recognition Request sent from a media gateway controller (MGC); performing speech recognition and enrolment according to the Speech Enrolment Start Request and the Speech Recognition Request, and obtaining a recognition and enrolment result; and feeding back the recognition and enrolment result to the MGC.

Claims

1. A method for performing speech recognition and enrollment, comprising:

receiving, by a media gateway (MG), a Speech Enrollment Start Request for triggering a grammar enrollment session from a media gateway controller (MGC);

after receiving the Speech Enrollment Start Request, establishing, by the MG, the grammar enrollment session according to the Speech Enrollment Start Request;

receiving, by the MG, a Speech Recognition Request instructing the MG to enroll a phrase in a grammar associated with the grammar enrollment session, from the MGC after the grammar enrollment session is established;

performing, by the MG, an enrollment for the phrase according to the Speech Recognition Request; and

sending, by the MG, an enrollment result to the MGC,

wherein the enrollment result is carried in a parameter of an Enrollment Results event of an H.248 protocol, the enrollment result comprises information indicating the number of consistent pronunciations that must still be obtained before the phrase is added to the grammar.

2. The method according to claim 1, wherein the number of consistent pronunciations that must still be obtained before the phrase is added to the grammar is zero, the method further comprises:

receiving, by the MG, an End Phrase Enrollment Request from the MGC, and according to the End Phrase Enrollment Request, adding the phrase in the grammar associated with the grammar enrollment session.

3. The method according to claims 1, wherein the Speech Enrollment Start Request is received through an enrollment start signal of an H.248 protocol.

4. The method according to claim 3, wherein the Speech Recognition Request is received through a header field or a speech recognition signal of the H.248 protocol.

5. A method for controlling speech recognition and enrollment, comprising:

sending, by a media gateway controller (MGC), a Speech Enrollment Start Request according to which a media gateway (MG) establishes a grammar enrollment session;

after the grammar enrollment session is established, sending, by the MGC, a Speech Recognition Request instructing the MG to enroll a phrase in a grammar associated with the grammar enrollment session, to the MG; and

receiving, by the MGC, an enrollment result sent from the MG,

wherein the enrollment result is carried in a parameter of an Enrollment Results event of an H.248 protocol, the parameter comprises information indicating the number of consistent pronunciations that must still be obtained before the phrase is added to the grammar.

6. The method according to claim 5, further comprising:

determining, by the MGC, that the number of consistent pronunciations that still be obtained before the phrase is added to the grammar is zero; and

sending, by the MGC, an End Phrase Enrollment Request to the MG to instruct the MG to add the phrase in the grammar associated with the grammar enrollment session.

7. The method according to claims 5, wherein the Speech Enrollment Start Request is sent through an enrollment start signal of the H.248 protocol.

8. A media gateway (MG), comprising:

a processor; and

a memory having a plurality of instructions stored thereon which, when executed by the processor, cause the processor to implement operations comprising;

receiving a Speech Enrollment Start Request from a media gateway controller (MGC);

establishing a grammar enrollment session according to the Speech Enrollment Start Request;

receiving a Speech Recognition Request instructing the MG to enroll a phrase in a grammar associated with the grammar enrollment session, which is sent from the MGC after the grammar enrollment session is established;

performing an enrollment for the phrase according to the Speech Recognition Request; and

sending an enrollment result to the MGC,

wherein the enrollment result is carried in a parameter of an Enrollment Results event of an H.248 protocol, the parameter comprises information indicating the number of consistent pronunciations that must still be obtained before the phrase is added to the grammar.

9. The MG according to claim 8, wherein the number of consistent pronunciations that must still be obtained before the phrase is added to the grammar is zero, the operations further comprises:

receiving an End Phrase Enrollment Request from the MGC, and according to the End Phrase Enrollment Request, adding the phrase in the grammar associated with the grammar enrollment session.

10. A media gateway controller (MGC), comprising:

a processor; and

a memory having a plurality of instructions which, when executed by the processor, cause the processor to implement operations comprising;

sending a Speech Enrollment Start Request according to which a media gateway (MG) establishes a grammar enrollment session;

sending a Speech Recognition Request instructing the MG to enroll a phrase in a grammar associated with the grammar enrollment session to the MG, after the grammar enrollment session is established; and

receiving an enrollment result sent from the MG,

wherein the enrollment result is carried in a parameter of an Enrollment Results event of an H.248 protocol, the parameter comprises information indicating the number of consistent pronunciations that must still be obtained before the phrase is added to the grammar.

11. The MGC according to claim 10, wherein the operations further comprise:

determining that the number of consistent pronunciations that must still be obtained before the phrase is added to the grammar is zero; and

sending an End Phrase Enrollment Request to the MG, the End Phrase Enrollment Request instructing the MG to add the phrase in the grammar associated with the grammar enrollment session.

12. A system comprising a media gateway controller (MGC) and a media gateway (MG), wherein:

the MGC is configured to send a Speech Enrollment Start Request for triggering a grammar enrollment session, and a Speech Recognition Request instructing the MG to enroll a phrase in a grammar associated with the grammar enrollment session, to the MG,

the MG is configured to;

receive the Speech Enrollment Start Request and establish the grammar enrollment session according to the Speech Enrollment Start Request;

perform an enrollment for the phrase according to the Speech Recognition Request; and

send an enrollment result to the MGC,

wherein the enrollment result is carried in a parameter of an Enrollment Results event of an H.248 protocol, the parameter comprises information indicating the number of consistent pronunciations that must still be obtained before the phrase is added to the grammar.