VOICE RECOGNITION METHOD, DEVICE, AND SYSTEM, AND COMPUTER STORAGE MEDIUM

• US 20170047066A1
• Filed: 11/25/2014
• Published: 02/16/2017
• Est. Priority Date: 04/30/2014
• Status: Abandoned Application

• Current Assignee: ZTE Corporation
• Original Assignee: ZTE Corporation
• Inventors: Liu, Haijun, Miao, Chuanyang
• Application Number:
  US15/307,023
• Publication Number:
  US 20170047066A1
• Time in Patent Office: Days
• US Class Current: 1/1
• CPC Class Codes: G10L 15/22 Procedures used during a speech recognition process, e.g. man-machine dialogue
• CPC Class Codes: G10L 15/30 Distributed recognition, e.g. in client-server systems, for mobile phones or network applications
• CPC Class Codes: G10L 2015/228 of application context

Abstract

Disclosed are a voice recognition method, device, and system, and a computer storage medium. One voice recognition method comprises: a voice recognition device releases a list of supported voices and/or a list of instructions corresponding to the supported voices. Another voice recognition method comprises: a voice recognition control device acquires a list of supported voices and/or a list of instructions corresponding to the voices supported by the voice recognition device.

Claims

1. A voice recognition method, comprising:

publishing, by a voice device, a list of supported voices and/or a list of instructions corresponding to the supported voices.

2. The voice recognition method according to claim 1, further comprising:

receiving, by the voice device, an acquired voice;

executing an instruction corresponding to the acquired voice;

or,

forwarding the acquired voice or the instruction corresponding to the acquired voice.

3. The voice recognition method according to claim 2, further comprising:

before executing the instruction corresponding to the acquired voice,

recognizing the acquired voice to obtain the instruction corresponding to the acquired voice.

4. The voice recognition method according to claim 2, wherein forwarding the acquired voice or the instruction corresponding to the acquired voice comprises:

forwarding the acquired voice or the instruction corresponding to the acquired voice according to a preset strategy, the preset strategy comprising at least one of the following strategies that;

when the acquired voice is a preset specific voice, the acquired voice or the instruction corresponding to the acquired voice is forwarded; and

when the acquired voice is not supported, the acquired voice or the instruction corresponding to the acquired voice is forwarded.

5. The voice recognition method according to claim 1, wherein publishing, by the voice device, the list of the supported voices and/or the list of the instructions corresponding to the supported voices comprises:

actively publishing, by the voice device, the list of the supported voices and/or the list of the instructions corresponding to the supported voices;

or

upon reception of a request message for querying a voice recognition capability, responding, by the voice device, with the list of the supported voices and/or the list of the instructions corresponding to the supported voices.

6. The voice recognition method according to claim 1, further comprising:

receiving, by the voice device, the instruction corresponding to the acquired voice, and executing the instruction.

7. The voice recognition method according to claim 1, wherein the voices in the list of the voices comprise at least one of voices in the following forms:

a voice text; and

coded voice data.

8. The voice recognition method according to claim 1, wherein

the list of the supported voices and/or the list of the instructions corresponding to the supported voices, which are/is published by the voice device, further comprise/comprises an identifier of the voice device;

and the identifier comprises at least one of identifiers in the following forms;

a voice text corresponding to the identifier of the voice device; and

coded voice data corresponding to the identifier of the voice device.

32. A computer storage medium having stored therein executable instructions used for executing the voice recognition method according to claim 1.

9. A voice recognition method, comprising:

acquiring, by a voice recognition control device, a list of voices supported by a voice device and/or a list of instructions corresponding to the voices supported by the voice device.

10. The voice recognition method according to claim 9, further comprising:

acquiring, by the voice recognition control device, a voice, and sending the acquired voice to the voice device.

11. The voice recognition method according to claim 9, further comprising:

acquiring, by the voice recognition control device, the voice, recognizing an instruction corresponding to the acquired voice and sending the recognized instruction to the voice device.

12. The voice recognition method according to claim 9, wherein

the voice comprises at least one of voices in the following forms:

a voice text; and

coded voice data.

13. The voice recognition method according to claim 9, further comprising:

acquiring, by the voice recognition control device, a voice;

determining a target voice device to be controlled which is instructed by the acquired voice; and

sending the acquired voice or an instruction corresponding to the acquired voice to the target voice device.

14. The voice recognition method according to claim 13, wherein each of the list of the voices supported by the voice device and the list of the instructions corresponding to the voices supported by the voice device comprises an identifier of the voice device.

15. The voice recognition method according to claim 14, wherein determining the target voice device to be controlled which is instructed by the acquired voice comprises:

recognizing the acquired voice, and matching a recognition result and identifiers of voice devices; and

determining the matched voice device as the target voice device to be controlled which is instructed by the acquired voice.

16. The voice recognition method according to claim 9, wherein the identifier of the voice device comprises at least one of identifiers in the following forms:

a voice text corresponding to the voice device; and

coded voice data corresponding to the voice device.

17. The voice recognition method according to claim 9, wherein acquiring, by the voice recognition control device, the list of the voices supported by the voice device and/or the list of the instructions corresponding to the supported voices comprises:

receiving, by the voice recognition control device, the list of the supported voices and/or the list of the instructions corresponding to the supported voices, which are/is published by the voice device;

or,

sending, by the voice recognition control device, a voice recognition capability request message to the voice device to receive the list of the supported voices and/or the list of the instructions corresponding to the supported voices, which are/is responded by the voice device.

33. A computer storage medium having stored therein executable instructions used for executing the voice recognition method according to claim 9.

18-30. -30. (canceled)

31. A voice recognition system, comprising a voice device and/or a voice recognition control device, wherein

the voice device is configured to publish a list of supported voices and/or a list of instructions corresponding to the supported voices;

and

the voice recognition control device is configured to acquire the list of the voices supported by the voice device and/or the list of the instructions corresponding to the voices supported by the voice device.