SPEECH RECOGNITION METHOD AND SPEECH RECOGNITION APPARATUS

• US 20150262577A1
• Filed: 07/08/2014
• Published: 09/17/2015
• Est. Priority Date: 08/29/2013
• Status: Active Grant

• Current Assignee: Safran Landing Systems UK Limited (Safran SA)
• Original Assignee: Panasonic Intellectual Property Corporation of America (Panasonic Holdings Corporation)
• Inventors: Nomura, Kazuya
• Granted Patent: US 9,865,255 B2
• Time in Patent Office: Days
• US Class Current: 1/1
• CPC Class Codes: G10L 15/1807 using prosody or stress
• CPC Class Codes: G10L 15/22 Procedures used during a speech recognition process, e.g. man-machine dialogue
• CPC Class Codes: G10L 17/22 Interactive procedures; Man-machine interfaces
• CPC Class Codes: G10L 2015/088 Word spotting
• CPC Class Codes: G10L 2015/223 Execution procedure of a spoken command
• CPC Class Codes: G10L 2015/227 of the speaker; Human-factor methodology

Abstract

A speech recognition apparatus that controls one or more devices by using speech recognition, including: a speech obtainer that obtains speech information representing speech spoken by a user; a speech recognition processor that recognizes the speech information, obtained by the speech obtainer, as character information; and a recognition result determiner that determines, based on the character information recognized by the speech recognition processor, whether the speech is spoken to the device(s).

Claims

1. A speech recognition method in a system that controls one or more devices by using speech recognition, comprising:

obtaining speech information representing speech spoken by a user;

recognizing the speech information, obtained in the obtaining, as character information; and

determining, based on the character information recognized in the recognizing, whether the speech is spoken to the one or more devices,

wherein at least one of the obtaining, the recognizing and the determining is performed by circuitry.

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

generating, in a case where it is determined in the determining that the speech is spoken to the one or more devices, an operation instruction for the one or more devices.

3. The speech recognition method according to claim 1, wherein the determining comprising:

analyzing a sentence pattern of the character information,

determining whether the sentence pattern is interrogative or imperative, and

determining, in a case where the sentence pattern is interrogative or imperative, that the speech is spoken to the one or more devices.

4. The speech recognition method according to claim 1, further comprising:

measuring, as a silent time, a time since obtaining of the speech information is completed; and

judging, in a case where the speech information is obtained, whether the measured silent time is greater than or equal to a certain time,

wherein the determining determines, in a case where it is determined that the measured silent time is greater than or equal to the certain time, the speech is spoken to the one or more devices.

5. The speech recognition method according to claim 1, further comprising:

storing in advance a certain keyword regarding an operation of the one or more devices,

wherein the determining determines whether the keyword, which is stored in advance, is included in the character information, and, in a case where the keyword is included in the character information, determines that the speech is spoken to the one or more devices.

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

storing in advance a personal name,

wherein the determining determines whether the personal name, which is stored in advance, is included in the character information, and, in a case where the personal name is included in the character information, determines that the speech is not spoken to the one or more devices.

7. The speech recognition method according to claim 1, further comprising:

detecting a person in a space where the one or more devices are located,

wherein the determining determines that the speech is not spoken to the one or more devices in response to detection of a plurality of people in the detecting, and determines that the speech is spoken to the one or more devices in response to detection of one person in the detecting.

8. The speech recognition method according to claim 1, wherein the determining determines whether a conjugated form of a declinable word or phrase included in the character information is imperative, and, in a case where the conjugated form is imperative, determines that the speech is spoken to the one or more devices.

9. The speech recognition method according to claim 1, further comprising:

adding weight values given in accordance with certain determination results for the character information,

wherein the determining determines whether a sum of the weight values added in the adding is greater than or equal to a certain value, and, in a case where the sum of the weight values is greater than or equal to the certain value, determines that the speech is spoken to the one or more devices.

10. The speech recognition method according to claim 9, wherein the adding adds a weight value given in accordance with whether a sentence pattern of the character information is interrogative or imperative, a weight value given in accordance with whether a silent time from when obtaining of the speech information is completed to when obtaining of next speech information is started is greater than or equal to a certain time, a weight value given in accordance with whether a pre-stored certain keyword regarding an operation of the one or more devices is included in the character information, a weight value given in accordance with whether a pre-stored personal name is included in the character information, a weight value given in accordance with whether a plurality of people is detected in a space where the one or more devices are located, and a weight value given in accordance with whether a conjugated form of a declinable word or phrase included in the character information is imperative.

11. The speech recognition method according to claim 2,

wherein the one or more devices include a mobile terminal,

wherein the operation instruction includes an operation instruction to obtain weather forecast for a day specified by the user and output the obtained weather forecast, and

wherein the generating outputs the generated operation instruction to the mobile terminal.

12. The speech recognition method according to claim 2,

wherein the one or more devices include a lighting device,

wherein the operation instruction includes an operation instruction to turn on the lighting device and an operation instruction to turn off the lighting device, and

wherein the generating outputs the generated operation instruction to the lighting device.

13. The speech recognition method according to claim 2,

wherein the one or more devices include a faucet device that automatically turns on water from an outlet,

wherein the operation instruction includes an operation instruction to turn on water from the faucet device, and an operation instruction to turn off water coming from the faucet device, and

wherein the generating outputs the generated operation instruction to the faucet device.

14. The speech recognition apparatus according to claim 2,

wherein the one or more devices include a television,

wherein the operation instruction includes an operation instruction to change a channel of the television, and

wherein the generating outputs the generated operation instruction to the television.

15. A speech recognition apparatus that controls one or more devices by using speech recognition, comprising:

one or more memories; and

circuitry which, in operation;

obtaining speech information representing speech spoken by a user;

recognizing the speech information, obtained in the obtaining, as character information; and

determining, based on the character information recognized in the recognizing, whether the speech is spoken to the one or more devices