ADJUSTING SPEECH RECOGNITION USING CONTEXTUAL INFORMATION

• US 20150213796A1
• Filed: 01/28/2014
• Published: 07/30/2015
• Est. Priority Date: 01/28/2014
• Status: Active Grant

• Current Assignee: Lenovo Singapore Pte Limited (Lenovo Group Ltd.)
• Original Assignee: Lenovo Singapore Pte Limited (Lenovo Group Ltd.)
• Inventors: Waltermann, Rod D., Cohen, Mark Evan
• Granted Patent: US 11,386,886 B2
• Time in Patent Office: Days
• US Class Current: 1/1
• 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 2015/228 of application context

Abstract

An embodiment provides a method, including: obtaining, using a processor, contextual information relating to an information handling device; adjusting, using a processor, an automated speech recognition engine using the contextual information; receiving, at an audio receiver of the information handling device, user speech input; and providing, using a processor, recognized speech based on the user speech input received and the contextual information adjustment to the automated speech recognition engine. Other aspects are described and claimed.

Claims

1. A method, comprising:

obtaining, using a processor, contextual information relating to an information handling device;

adjusting, using a processor, an automated speech recognition engine using the contextual information;

receiving, at an audio receiver of the information handling device, user speech input; and

providing, using a processor, recognized speech based on the user speech input received and the contextual information adjustment to the automated speech recognition engine.

2. The method of claim 1, wherein said adjusting comprises selecting a knowledge domain based on the contextual information.

3. The method of claim 1, wherein said adjusting comprises selecting a lexicon based on the contextual information.

4. The method of claim 1, wherein said adjusting comprises weighting one or more words based on the contextual information.

5. The method of claim 1, further comprising committing a predetermined action matching the recognized speech;

wherein said adjusting comprises adjusting the matching between recognized speech and a predetermined action based on the contextual information.

6. The method of claim 1, further comprising:

providing a communication to the user including estimated recognized speech based on the user speech input and the contextual information adjustment to the automated speech recognition engine; and

committing a predetermined action matching the recognized speech.

7. The method of claim 6, further comprising receiving user input associated with the communication;

wherein said committing a predetermined action matching the recognized speech proceeds responsive thereto.

8. The method of claim 1, wherein said contextual information is selected from the group consisting of contextual information relating to user interaction with the information handling device, contextual information relating to running applications of the information handling device, contextual information relating to received stimulus of the information handling device, and contextual information relating to sensed environment of the information handling device.

9. The method of claim 1, wherein the contextual information is derived from the information handling device.

10. The method of claim 1, wherein the contextual information is transferrable to another information handling device.

11. An information handling device, comprising:

an audio receiver;

a processor operatively coupled to the audio receiver; and

a memory device storing instructions executable by the processor to;

obtain contextual information relating to the information handling device;

adjust an automated speech recognition engine using the contextual information;

receive, at the audio receiver, user speech input; and

provide recognized speech based on the user speech input received and the contextual information adjustment to the automated speech recognition engine.

12. The information handling device of claim 11, wherein to adjust comprises selecting a knowledge domain based on the contextual information.

13. The information handling device of claim 11, wherein to adjust comprises selecting a lexicon based on the contextual information.

14. The information handling device of claim 11, wherein to adjust comprises weighting one or more words based on the contextual information.

15. The information handling device of claim 11, wherein the instructions are further executable by the processor to commit a predetermined action matching the recognized speech;

wherein to adjust comprises adjusting the matching between recognized speech and a predetermined action based on the contextual information.

16. The information handling device of claim 11, wherein the instructions are further executable by the processor to:

provide a communication to the user including estimated recognized speech based on the user speech input and the contextual information adjustment to the automated speech recognition engine; and

commit a predetermined action matching the recognized speech.

17. The information handling device of claim 16, wherein the instructions are further executable by the processor to receive user input associated with the communication;

wherein committing of a predetermined action matching the recognized speech proceeds responsive thereto.

18. The information handling device of claim 11, wherein said contextual information is selected from the group consisting of contextual information relating to user interaction with the information handling device, contextual information relating to running applications of the information handling device, contextual information relating to received stimulus of the information handling device, and contextual information relating to sensed environment of the information handling device.

19. The information handling device of claim 11, wherein the contextual information is derived from the information handling device.

20. A program product, comprising:

a storage medium comprising device readable program code, the code being executable by a processor and comprising;

code that obtains, using a processor, contextual information relating to an information handling device;

code that adjusts, using a processor, an automated speech recognition engine using the contextual information;

code that receives, at an audio receiver of the information handling device, user speech input; and

code that provides, using a processor, recognized speech based on the user speech input received and the contextual information adjustment to the automated speech recognition engine.