CONTROLLER FOR VOICE-CONTROLLED DEVICE AND ASSOCIATED METHOD

• US 20150039305A1
• Filed: 08/04/2014
• Published: 02/05/2015
• Est. Priority Date: 08/02/2013
• Status: Active Grant

• Current Assignee: Xueshan Technologies Inc. (Wi-LAN Inc.)
• Original Assignee: MStar Semiconductor Incorporated (MediaTek, Inc.)
• Inventors: Huang, Hung-Chi
• Granted Patent: US 9,330,664 B2
• Time in Patent Office: Days
• US Class Current: 704/233
• CPC Class Codes: G10L 15/01 Assessment or evaluation of speech recognition systems
• CPC Class Codes: G10L 15/10 using distance or distortion measures between unknown speech and reference templates
• CPC Class Codes: G10L 15/20 Speech recognition techniques specially adapted for robustness in adverse environments, e.g. in noise, of stress induced speech G10L21/02 takes precedence

Abstract

A controller for a voice-controlled device is provided. The controller includes a setting module and a recognition module. The setting module generates a threshold according to an environmental parameter. The recognition module compares a confident score of speech recognition with the threshold to accordingly execute voice control.

Claims

1. A controller for a voice-controlled device, comprising:

a setting module, configured to generate a threshold according to an environmental parameter associated with an environment that the voice-controlled device disposed in; and

a recognition module, configured to receive a speech, to perform speech recognition on the speech to generate a confidence score of speech recognition, and to compare the confidence score of speech recognition with the threshold to generate a control signal.

2. The controller according to claim 1, wherein the environmental parameter is a volume value.

3. The controller according to claim 1, further comprising an environment detector configured to detect the environment to obtain the environmental parameter.

4. The controller according to claim 3, wherein the environment detector is configured to detect a volume of the environment.

5. The controller according to claim 3, wherein the environment detector is configured to detect a brightness of the environment.

6. The controller according to claim 1, wherein the environmental parameter is a time value.

7. The controller according to claim 1, wherein the controller comprises a storage unit, the storage unit is configured to store a look-up table (LUT), and the setting module looks up the LUT according to the environmental parameter to generate the threshold.

8. A method for a voice-controlled device, comprising:

generating a threshold according to an environmental parameter associated with an environment that the voice-controlled device disposed in;

receiving a speech, and performing speech recognition on the speech to generate a confidence score of speech recognition; and

comparing the confidence score of speech recognition with the threshold to generate a control signal.

9. The method according to claim 8, wherein the environmental parameter is a volume value.

10. The method according to claim 8, wherein the environmental parameter is obtained by detecting a volume of the environment.

11. The method according to claim 8, wherein the environmental parameter is obtained by detecting a brightness of the environment.

12. The method according to claim 8, wherein the environmental parameter is a time value.

13. The method according to claim 8, wherein the step of generating the threshold according to the environmental parameter comprises:

looking up an LUT according to the environmental parameter to generate the threshold.