Voice Interaction Method And Apparatus

• US 20150255072A1
• Filed: 05/22/2015
• Published: 09/10/2015
• Est. Priority Date: 11/26/2012
• Status: Active Grant

• Current Assignee: Tencent Technology Shenzhen Company Limited (Tencent Holdings Limited)
• Original Assignee: Tencent Technology Shenzhen Company Limited (Tencent Holdings Limited)
• Inventors: ZHOU, Bin
• Granted Patent: US 9,728,192 B2
• Time in Patent Office: Days
• US Class Current: 1/1
• CPC Class Codes: G10L 15/06 Creation of reference templates; Training of speech recognition systems, e.g. adaptation to the characteristics of the speaker's voice G10L15/14 takes precedence
• CPC Class Codes: G10L 17/22 Interactive procedures; Man-machine interfaces
• CPC Class Codes: G10L 2015/0638 Interactive procedures
• CPC Class Codes: G10L 2015/088 Word spotting

Abstract

A voice interaction method and apparatus is described. The method includes setting a correspondence between an image material movement command and an interaction keyword. The method also includes displaying an image material, recording a user voice file and parsing the user voice file so as to obtain an interaction keyword. The method also includes determining, according to the interaction keyword obtained by parsing, an image material movement command corresponding to the interaction keyword, and controlling movement of the image material based on the determined image material movement command.

Claims

1. A voice interaction method, comprising:

setting a correspondence between an image material movement command and an interaction keyword, and further comprising;

displaying an image material;

recording a user voice file, and parsing the user voice file so as to obtain an interaction keyword; and

determining, according to the interaction keyword obtained by parsing, an image material movement command corresponding to the interaction keyword, and controlling movement of the image material based on the determined image material movement command.

2. The voice interaction method according to claim 1, wherein the parsing the user voice file so as to obtain the interaction keyword comprises:

acquiring a voice training file and a text training file, estimating a voice parameter of a voice recognizer in a voice adaptive manner by using the voice training file and the text training file, and identifying the user voice file by using the voice recognizer whose voice parameter has been estimated, so as to convert the user voice file into a text file; and

retrieving the interaction keyword from the text file.

3. The voice interaction method according to claim 1, wherein the parsing the user voice file so as to obtain the interaction keyword comprises:

determining a speech waveform diagram of the user voice file; and

determining whether the speech waveform diagram of the user voice file comprises a waveform area consistent with a speech waveform of the interaction keyword, and if yes, determining the interaction keyword based on the comprised speech waveform of the interaction keyword.

4. The voice interaction method according to claim 1, wherein the setting a correspondence between an image material movement command and an interaction keyword is:

setting a correspondence between an image material acceleration command, an image material deceleration command, an image material start command, an image material stop command, an image material moving speed maintenance command, or an image material moving track and the interaction keyword.

5. The voice interaction method according to claim 1, comprising:

further setting a correspondence between an image material change command and an image material change keyword, wherein the method further comprises;

recording the user voice file, and parsing the user voice file so as to obtain an image material change keyword; and

determining, according to the image material change keyword obtained by parsing, an updated image material corresponding to the image material change keyword, and displaying the updated image material.

6. A voice interaction apparatus, comprising one or more processors and a memory, the memory comprising multiple units that can be executed by the one or more processors, and the multiple units comprise:

a correspondence setting unit, an image material display unit, an interaction keyword parsing unit, and an image material movement unit,

the correspondence setting unit being configured to set a correspondence between an image material movement command and an interaction keyword;

the image material display unit being configured to display an image material;

the interaction keyword parsing unit being configured to record a user voice file, and parse the user voice file so as to obtain an interaction keyword; and

the image material movement unit being configured to determine, according to the interaction keyword obtained by parsing, an image material movement command corresponding to the interaction keyword, and control movement of the image material based on the determined image material movement command.

7. The voice interaction apparatus according to claim 6, wherein

the interaction keyword parsing unit is configured to acquire a voice training file and a text training file, estimate a voice parameter of a voice recognizer in a voice adaptive manner by using the voice training file and the text training file, and identify the user voice file by using the voice recognizer whose voice parameter has been estimated, so as to convert the user voice file into a text file;

and retrieve the interaction keyword from the text file.

8. The voice interaction apparatus according to claim 6, wherein

the interaction keyword parsing unit is configured to determine a speech waveform diagram of the user voice file;

and determine whether the speech waveform diagram of the user voice file comprises a waveform area consistent with a speech waveform of the interaction keyword, and if yes, determine the interaction keyword based on the comprised speech waveform of the interaction keyword.

9. The voice interaction apparatus according to claim 6, wherein

the correspondence setting unit is configured to set a correspondence between an image material acceleration command, an image material deceleration command, an image material start command, an image material stop command, an image material moving speed maintenance command, or an image material moving track and the interaction keyword.

10. The voice interaction apparatus according to claim 6, further comprising an image material change unit, wherein

the correspondence setting unit is further configured to set a correspondence between an image material change command and an image material change keyword;

the interaction keyword parsing unit is further configured to record the user voice file, and parse the user voice file so as to obtain an image material change keyword;

the image material change unit is configured to determine, according to the image material change keyword obtained by parsing, an updated image material corresponding to the image material change keyword, and send the updated image material to the image material display unit; and

the image material display unit is further configured to display the updated image material.

11. A mobile terminal, comprising one or more processors and a memory, the memory comprising multiple units which can be executed by the one or more processors, and the multiple units comprise:

a display unit, a voice recording unit, and a calculation unit,

the display unit being configured to display an image material;

the voice recording unit being configured to record a user voice file; and

the calculation unit being configured to store a correspondence between an image material movement command and an interaction keyword, and parse the user voice file so as to obtain an interaction keyword; and

determine, according to the interaction keyword obtained by parsing, an image material movement command corresponding to the interaction keyword, and control movement of the image material based on the determined image material movement command.

12. The mobile terminal according to claim 11, wherein the calculation unit is further configured to:

acquire a voice training file and a text training file, estimate a voice parameter of a voice recognizer in a voice adaptive manner by using the voice training file and the text training file, and identify the user voice file by using the voice recognizer whose voice parameter has been estimated, so as to convert the user voice file into a text file; and

retrieve the interaction keyword from the text file.

13. The mobile terminal according to claim 11, wherein the calculation unit is further configured to:

determine a speech waveform diagram of the user voice file; and

determine whether the speech waveform diagram of the user voice file comprises a waveform area consistent with a speech waveform of the interaction keyword, and if yes, determine the interaction keyword based on the comprised speech waveform of the interaction keyword.

14. The mobile terminal according to claim 11, wherein the correspondence between an image material movement command and an interaction keyword comprises:

a correspondence between an image material acceleration command, an image material deceleration command, an image material start command, an image material stop command, an image material moving speed maintenance command, or an image material moving track and the interaction keyword.

15. The mobile terminal according to claim 11, wherein the calculation unit is further configured to store a correspondence between an image material change command and an image material change keyword;

and

the calculation unit is further configured to;

parse the user voice file so as to obtain the image material change keyword; and

determine, according to the image material change keyword obtained by parsing, an updated image material corresponding to the image material change keyword, and control the display unit to display the updated image material.

16. The mobile terminal according to claim 11, further comprising a photographing unit, wherein

the photographing unit is further configured to sense heat of a user, and send a heat prompt message to the display unit after the heat of the user is sensed;

and

the display unit is further configured to;

after the heat prompt message is received, play an image material movement start audio.