METHOD AND APPARATUS FOR PERFORMING VOICE RECOGNITION ON BASIS OF DEVICE INFORMATION

• US 20160232894A1
• Filed: 04/07/2016
• Published: 08/11/2016
• Est. Priority Date: 10/08/2013
• Status: Active Grant

• Current Assignee: Samsung Electronics Co. Ltd.
• Original Assignee: Samsung Electronics Co. Ltd.
• Inventors: KIM, Nam-hoon, LEE, Kyung-min, PARK, Chi-youn, LEE, Cheong-jae, LEE, Jae-won
• Granted Patent: US 10,636,417 B2
• Time in Patent Office: Days
• US Class Current: 1/1
• CPC Class Codes: G10L 15/063 Training
• CPC Class Codes: G10L 15/19 Grammatical context, e.g. disambiguation of the recognition hypotheses based on word sequence rules
• CPC Class Codes: G10L 15/34 Adaptation of a single recogniser for parallel processing, e.g. by use of multiple processors or cloud computing
• CPC Class Codes: G10L 2015/0635 updating or merging of old and new templates; Mean values; Weighting
• CPC Class Codes: G10L 2015/228 of application context

Abstract

A method of obtaining a grammar model to perform speech recognition includes obtaining information about a state of at least one device, obtaining grammar model information about the at least one device based on the obtained information, and generating a grammar model to perform the speech recognition based on the obtained grammar model information.

Claims

1. A method of obtaining a grammar model to perform speech recognition, the method comprising:

obtaining information about a state of at least one device;

obtaining grammar model information about the at least one device based on the obtained information; and

generating a grammar model to perform the speech recognition based on the obtained grammar model information.

2. The method of claim 1, wherein the information about the state of the at least one device comprises at least one of information about an operation state of each device, information about whether each device is controllable, information about a position where each device is installed or connected, and an operation that is performable in each device.

3. The method of claim 1, wherein the grammar model information comprises at least one piece of pattern information in which a text string is to be inserted based on the information about the state of the at least one device, and the generating of the grammar model comprises:

obtaining a pronunciation table to determine the text string to be inserted in the pattern information;

obtaining at least one text string corresponding to the pattern information according to the information about the state of the at least one device, from the pronunciation table; and

obtaining the grammar model information about the at least one device by inserting the obtained text string in the pattern information included in the grammar model information.

4. The method of claim 1, further comprising performing speech recognition based on the generated grammar model.

5. The method of claim 1, wherein, whenever the state of the at least one device changes, the information about the state of the at least one device is obtained, the grammar model information is obtained based on the obtained information, and the grammar model is generated based on the obtained grammar model information.

6. The method of claim 1, wherein, when the at least one device is a probe, the grammar model information about the device comprises an app or preset set with respect to the probe, or a control command that is executable in an ultrasound apparatus of the probe, according to a type of the probe.

13. A non-transitory computer readable storage medium having stored thereon a program, which when executed by a computer, performs the method defined in claim 1.

7. An apparatus for obtaining a grammar model to perform speech recognition, the apparatus comprising:

a receiving portion obtaining information about a state of at least one device and obtaining grammar model information about the at least one device based on the obtained information; and

a control portion generating a grammar model to perform the speech recognition based on the obtained grammar model information.

8. The apparatus of claim 7, wherein the information about the state of the at least one device comprises at least one of information about an operation state of each device, information about whether each device is controllable, information about a position where each device is installed or connected, and an operation that is performable in each device.

9. The apparatus of claim 7, wherein the grammar model information comprises at least one piece of pattern information that is determined based on the information about the state of the at least one device,

the receiving portion obtains a pronunciation table to determine a text string to be inserted in the pattern information, and

the control portion obtains at least one text string corresponding to the pattern information according to the information about the state of the at least one device, from the pronunciation table, and obtains the grammar model information about the at least one device by inserting the obtained text string in the pattern information included in the grammar model information.

10. The apparatus of claim 7, wherein, when the at least one device is a probe, the grammar model information about the at least one device comprises an app or preset set with respect to the probe, or a control command that is executable in an ultrasound apparatus of the probe, according to a type of the probe.

11. The apparatus of claim 7, wherein the control portion performs speech recognition based on the generated grammar model.

12. The apparatus of claim 7, wherein, whenever the state of the at least one device changes, the information about the state of the at least one device is obtained, the grammar model information is obtained based on the obtained information, and the grammar model is generated based on the obtained grammar model information.