DEVICE INCLUDING SPEECH RECOGNITION FUNCTION AND METHOD OF RECOGNIZING SPEECH

• US 20150294666A1
• Filed: 06/25/2015
• Published: 10/15/2015
• Est. Priority Date: 12/28/2012
• Status: Active Grant

• Current Assignee: Socionext Inc.
• Original Assignee: Socionext Inc.
• Inventors: MIYASAKA, Shuji, ABE, Kazutaka
• Granted Patent: US 9,792,902 B2
• Time in Patent Office: Days
• US Class Current: 1/1
• CPC Class Codes: G10L 13/00 Speech synthesis; Text to speech systems
• CPC Class Codes: G10L 15/08 Speech classification or search
• CPC Class Codes: G10L 15/22 Procedures used during a speech recognition process, e.g. man-machine dialogue
• CPC Class Codes: G10L 15/222 Barge in, i.e. overridable guidance for interrupting prompts
• CPC Class Codes: G10L 15/28 Constructional details of speech recognition systems
• 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 2021/02082 the noise being echo, reverberation of the speech
• CPC Class Codes: G10L 21/0208 Noise filtering

Abstract

A device including a speech recognition function which recognizes speech from a user, includes: a loudspeaker which outputs speech to a space; a microphone which collects speech in the space; a first speech recognition unit which recognizes the speech collected by the microphone; a command control unit which issues a command for controlling the device, based on the speech recognized by the first speech recognition unit; and a control unit which prohibits the command issuance unit from issuing the command, based on the speech to be output from the loudspeaker.

Claims

1. A device including a speech recognition function which recognizes user speech which is speech from a user, the device comprising:

a loudspeaker which outputs speech to a space;

a microphone which collects speech in the space;

a first speech recognition unit configured to recognize the speech collected by the microphone;

a command issuance unit configured to issue a command for controlling the device including the speech recognition function, based on the speech recognized by the first speech recognition unit; and

a control unit configured to prohibit the command issuance unit from issuing the command, based on the speech to be output from the loudspeaker.

2. The device including the speech recognition function according to claim 1,

wherein the control unit includes a second speech recognition unit configured to recognize the speech to be output from the loudspeaker, and

the control unit is configured to determine whether or not the speech recognized by the second speech recognition unit matches a predetermined keyword, and when the speech recognized by the second speech recognition unit matches the predetermined keyword, prohibit the command issuance unit from issuing the command.

3. A device including a speech recognition function which recognizes user speech which is speech from a user, the device comprising:

at least one loudspeaker which outputs speech to a space;

a microphone which collects speech in the space;

a speech recognition unit configured to recognize the user speech among the speech collected by the microphone;

a downsampler which downsamples a speech signal to have a narrower bandwidth, the speech signal being an electric signal of the speech to be output from the at least one loudspeaker; and

an echo canceller which estimates, based on the speech signal downsampled, an echo component which is the speech collected by the microphone among the speech output from the at least one loudspeaker, and cancels the echo component estimated, from the speech collected by the microphone,

wherein the speech recognition unit is configured to recognize the user speech by recognizing speech from which the echo canceller has canceled the echo component.

4. The device including the speech recognition function according to claim 3,

wherein the downsampler downsamples the speech signal input to the downsampler, by less than or equal to (1/N)̂

0.5, when the at least one loudspeaker comprises N loudspeakers, N being an integer greater than or equal to 2.

5. The device including the speech recognition function according to claim 3, further comprising

a command issuance unit configured to issue a command for controlling the device including the speech recognition function, based on the speech recognized by the speech recognition unit,

wherein the speech recognition unit is configured to prohibit the command issuance unit from issuing the command based on the echo component, by recognizing speech from which the echo canceller has canceled the echo component.

6. A method of recognizing user speech which is speech from a user, the method comprising:

outputting speech to a space;

collecting speech in the space after the outputting;

recognizing the speech collected in the collecting;

issuing a command for controlling a device including a speech recognition function, based on the speech recognized in the recognizing, the issuing being performed by a command issuance unit; and

prohibiting the command issuance unit from issuing the command, based on the speech to be output in the outputting.

7. A method of recognizing user speech which is speech from a user, the method comprising:

outputting speech to a space;

collecting speech in the space after the outputting;

recognizing the user speech among the speech collected in the collecting;

downsampling a speech signal to have a narrower bandwidth, the speech signal being an electric signal of the speech to be output in the outputting; and

estimating, based on the speech signal downsampled, an echo component which is the speech collected in the collecting among the speech output in the outputting, and canceling the echo component estimated, from the speech collected in the collecting;

wherein in the recognizing, the user speech is recognized by recognizing speech from which the echo component has been canceled in the canceling.