Speech recognition terminal device, speech recognition system, and speech recognition method

• US 9,349,371 B2
• Filed: 01/13/2015
• Issued: 05/24/2016
• Est. Priority Date: 01/17/2014
• Status: Active Grant

• Current Assignee: DENSO Corporation
• Original Assignee: DENSO Corporation
• Inventors: Fujisawa, Yuki, Nada, Toru
• Primary Examiner(s): Pullias, Jesse
• Application Number:
  US14/595,379
• Publication Number:
  US 20150206531A1
• Time in Patent Office: 497 Days
• Field of Search: 704231-257, 704270-275
• US Class Current: 1/1
• CPC Class Codes: G10L 15/22 Procedures used during a speech recognition process, e.g. man-machine dialogue
• CPC Class Codes: G10L 15/30 Distributed recognition, e.g. in client-server systems, for mobile phones or network applications

Abstract

A speech recognition terminal device communicable with a speech recognition server includes a request device for requesting the speech recognition server to carry out the speech recognition of an acquired speech command, a prediction device for predicting a present delay time until a result of the requested speech recognition is obtained from the speech recognition server, a determination device for determining a filler word with a time length in accordance with the predicted present delay time, a filler speaking device for outputting the determined filler word during a waiting time until the result of the requested speech recognition is obtained from the speech recognition server, and a response device for responding to the user when the result of the speech recognition is acquired from the speech recognition server.

Claims

1. A speech recognition terminal device capable of communicating with a speech recognition server that carries out speech recognition, the speech recognition terminal device comprising:

a speech acquisition device that acquires a speech command spoken by a user;

a request device that requests the speech recognition server to carry out the speech recognition of the speech command acquired by the speech acquisition device;

a prediction device that predicts a present delay time until a result of the speech recognition of the speech command requested from the request device is obtained from the speech recognition server;

a determination device that determines a filler word with a time length in accordance with the present delay time predicted by the prediction device;

a filler speaking device that outputs the filler word determined by the determination device as speech information during a waiting time until the result of the speech recognition requested from the request device is obtained from the speech recognition server;

a response device that, when the result of the speech recognition is acquired from the speech recognition server, executes a process of responding to the user based on the acquired result of the speech recognition; and

an acquiring device that acquires time information expressing past delay times when the communication has been carried out with the speech recognition server in past, wherein

based on the past delay times expressed by the time information acquired by the acquisition device, the prediction device predicts the present delay time until the result of the speech recognition requested from the request device is obtained from the speech recognition server.

2. The speech recognition terminal device according to claim 1, wherein:

the acquiring device acquires time information expressing the present delay time when the speech recognition is requested of the speech recognition server by the request device and the result of the speech recognition pertaining to the request is obtained from the speech recognition server.

3. The speech recognition terminal device according to claim 1, wherein:

the acquisition device acquires time information expressing a test delay time measured by test communication with the speech recognition server.

4. The speech recognition terminal device according to claim 1, wherein:

the time information acquired by the acquiring device is association with a time of the communication, and

based on the past delay times expressed by the time information associated with the communication carried out immediately prior to, or during a period near, a present time point, the prediction device predicts the present delay time until the result of the speech recognition is obtained from the speech recognition server.

5. The speech recognition terminal device according to claim 1, wherein:

the time information acquired by the acquiring device is associated with a location where the communication is carried out; and

based on the past delay times expressed by the time information associated with the communication carried out within a predetermined geographical range with respect to a present position, the prediction device predicts the present delay time until the result of the speech recognition is obtained from the speech recognition server.

6. A speech recognition system comprising:

the speech recognition terminal device according to claim 1; and

a speech recognition server that is capable of communicating with the speech recognition terminal device,

wherein

the speech recognition server includes;

a recognition device that receives a request from the speech recognition terminal device to carry out the speech recognition of a speech command and carries out the speech recognition of the requested speech command; and

a notification device that notifies the speech recognition terminal device, which is a sender of the request, of the result of the speech recognition by the recognition device.

7. A speech recognition terminal device capable of communicating with a speech recognition server that carries out speech recognition, the speech recognition terminal device comprising:

a speech acquisition device that acquires a speech command spoken by a user;

a request device that requests the speech recognition server to carry out the speech recognition of the speech command acquired by the speech acquisition device;

a prediction device that predicts a present delay time until a result of the speech recognition of the speech command requested from the request device is obtained from the speech recognition server;

a determination device that determines a filler word with a time length in accordance with the present delay time predicted by the prediction device;

a filler speaking device that outputs the filler word determined by the determination device as speech information during a waiting time until the result of the speech recognition requested from the request device is obtained from the speech recognition server;

a response device that, when the result of the speech recognition is acquired from the speech recognition server, executes a process of responding to the user based on the acquired result of the speech recognition; and

an acquiring device that acquires from an external device time information expressing past delay times when the speech recognition server has communicated with the speech recognition terminal device in past, wherein

based on the past delay times expressed by the time information acquired from the external device by the acquiring device, the prediction device predicts the present delay time until the result of the speech recognition is obtained from the speech recognition server.

8. A speech recognition terminal device capable of communicating with a speech recognition server that carries out speech recognition, the speech recognition terminal device comprising:

a speech acquisition device that acquires a speech command spoken by a user;

a request device that requests the speech recognition server to carry out the speech recognition of the speech command acquired by the speech acquisition device;

a prediction device that predicts a present delay time until a result of the speech recognition of the speech command requested from the request device is obtained from the speech recognition server;

a determination device that determines a filler word with a time length in accordance with the present delay time predicted by the prediction device;

a filler speaking device that outputs the filler word determined by the determination device as speech information during a waiting time until the result of the speech recognition requested from the request device is obtained from the speech recognition server;

a response device that, when the result of the speech recognition is acquired from the speech recognition server, executes a process of responding to the user based on the acquired result of the speech recognition;

an extension prediction device that, in cases where the result of the speech recognition is not acquired from the speech recognition server at a time when the present delay time predicted by the prediction device elapses, predicts an extension time when the result of the speech recognition will be obtained;

an extension determination device that determines an extension filler word with a time length in accordance with the extension time predicted by the extension prediction device; and

an extension filler speaking device that outputs the extension filler word determined by the extension determination device as speech information during the waiting time until the result of the speech recognition is obtained from the speech recognition server.

9. A speech recognition method in a computer system that carries out speech recognition, the speech recognition method comprising:

performing an acquisition process including acquiring a speech command spoken by a user;

performing a request process including requesting a speech recognition server that carries out speech recognition of the speech command acquired in the acquisition process;

performing a prediction process including predicting a present delay time until a result of the speech recognition requested in the request process is obtained from the speech recognition server;

performing a determination process including determining a filler word with a time length in accordance with the present delay time predicted in the prediction process;

performing a filler speaking process including outputting the filler word, which is determined in the determination process, as speech information during a waiting time until the result of the speech recognition requested in the request process is obtained from the speech recognition server;

when the result of the speech recognition is acquired from the speech recognition server, performing a response process including responding to the user based on the acquired result of the speech recognition; and

performing an acquiring process including acquiring time information expressing past delay times when communication has been carried out with the speech recognition server in past, wherein;

in the prediction process, the present delay time until the result of the speech recognition is obtained from the speech recognition server is predicted based on the past delay times expressed by the time information acquired in the acquiring process.

10. The speech recognition method according to claim 9, wherein:

the acquiring process includes acquiring time information expressing the present delay time when the speech recognition is requested of the speech recognition server and the result of the requested speech recognition is obtained from the speech recognition server.

11. The speech recognition method according to claim 9, wherein:

the acquiring process includes acquiring time information expressing a test delay time measured by test communication with the speech recognition server.

12. The speech recognition method according to claim 9, wherein:

the time information is associated with a time of the communication; and

in the prediction process, the present delay time until the result of the speech recognition is obtained from the speech recognition server is predicted based on the past delay times expressed by the time information associated with the communication carried out immediately prior to, or during a period near, a present time point.

13. The speech recognition method according to claim 9, wherein:

the time information is associated with a location where the communication is carried out; and

in the prediction process, the present delay time until the result of the speech recognition is obtained from the speech recognition server is predicted based on the past delay times expressed by the time information associated with the communication carried out within a predetermined geographical range with respect to a present location.

14. A speech recognition method in a computer system that carries out speech recognition, the speech recognition method comprising:

performing an acquisition process including acquiring a speech command spoken by a user;

performing a request process including requesting a speech recognition server that carries out speech recognition of the speech command acquired in the acquisition process;

performing a prediction process including predicting a present delay time until a result of the speech recognition requested in the request process is obtained from the speech recognition server;

performing a determination process including determining a filler word with a time length in accordance with the present delay time predicted in the prediction process;

performing a filler speaking process including outputting the filler word, which is determined in the determination process, as speech information during a waiting time until the result of the speech recognition requested in the request process is obtained from the speech recognition server;

when the result of the speech recognition is acquired from the speech recognition server, performing a response process including responding to the user based on the acquired result of the speech recognition; and

performing an acquiring process including acquiring time information stored in an external device as information expressing past delay times when the speech recognition server has communicated with a remote speech recognition terminal device in past, wherein;

in the prediction process, the present delay time until the result of the speech recognition is obtained from the speech recognition server is predicted based on the past delay times expressed by the time information acquired from the external device.

15. A speech recognition method in a computer system that carries out speech recognition, the speech recognition method comprising:

performing an acquisition process including acquiring a speech command spoken by a user;

performing a request process including requesting a speech recognition server that carries out speech recognition of the speech command acquired in the acquisition process;

performing a prediction process including predicting a present delay time until a result of the speech recognition requested in the request process is obtained from the speech recognition server;

performing a determination process including determining a filler word with a time length in accordance with the present delay time predicted in the prediction process;

performing a filler speaking process including outputting the filler word, which is determined in the determination process, as speech information during a waiting time until the result of the speech recognition requested in the request process is obtained from the speech recognition server;

when the result of the speech recognition is acquired from the speech recognition server, performing a response process including responding to the user based on the acquired result of the speech recognition;

performing an extension determination process including, when the result of the speech recognition is not acquired from the speech recognition server at a time when the predicted present delay time elapses, predicting an extension time when the result of the speech recognition will be obtained;

performing a determining process including determining an extension filler word with a time length in accordance with the extension time predicted in the extension determination process; and

performing an extension filler speaking process including outputting the determined extension filler word as speech information during a waiting time until the result of the speech recognition is obtained from the speech recognition server.