Voice recognition system, communication terminal, voice recognition server and program

• US 20040030553A1
• Filed: 06/23/2003
• Published: 02/12/2004
• Est. Priority Date: 06/25/2002
• Status: Active Grant

• Current Assignee: DENSO Corporation
• Original Assignee: DENSO Corporation
• Inventors: Asada, Hiroshige, Ito, Toshiyuki
• Granted Patent: US 7,356,471 B2
• Time in Patent Office: Days
• US Class Current: 704/246
• CPC Class Codes: G10L 15/065 Adaptation
• CPC Class Codes: G10L 15/30 Distributed recognition, e.g. in client-server systems, for mobile phones or network applications

Abstract

A voice recognition system has a vehicle unit, which is a communication terminal, and a voice recognition server. The voice recognition server recognizes a voice signal received from the vehicle unit. A sound characteristic of a communication channel for providing communication between the vehicle unit and the server requires to be adjusted so that the server properly recognizes the voice signal. A test pattern signal is used for adjusting the sound characteristic. The vehicle unit adjusts the sound characteristic based on the test pattern signal. Therefore, the server does not require a large database for the sound characteristic adjustment because it is performed by the vehicle unit.

Claims

1. A voice recognition system comprising:

a communication terminal that transmits a voice signal through a communication network; and

a voice recognition server that recognizes the voice signal received from the communication terminal,

wherein the communication terminal adjusts a sound characteristic of the communication network for providing communication between the communication terminal and the voice recognition server.

2. The voice recognition system according to claim 1, wherein:

the voice recognition server transmits a second voice signal to the communication terminal,

the communication terminal produces a sound based on the second voice signal, receives the sound as a loop back voice signal, and transmits the loop back voice signal,

the voice recognition server receives and analyzes the loop back voice signal, and produces an adjustment data based on the analysis, the adjustment data represents a sound characteristic of the communication network, and

the communication terminal adjusts the sound characteristic based on the adjustment data.

3. The voice recognition system according to claim 2, wherein:

the second voice signal transmitted by the voice recognition server is a test pattern voice signal created by an electrical composition, and

the communication terminal adjusts the sound characteristic of the communication network based on the adjustment data produced by the test pattern voice signal.

4. The voice recognition system according to claim 2, wherein:

the second voice signal transmitted by the voice recognition server is a voice signal that is created by a word of an operator of the voice recognition server, and

the communication terminal adjusts the sound characteristic of the communication network based on the adjustment data produced by the second voice signal.

5. A communication terminal used in a voice recognition system, for sending a voice signal to a voice recognition server via a communication network, the voice recognition server recognizes the voice signal received from the communication terminal, the communication terminal comprising:

an adjustment means for adjusting a sound characteristic of the communication network for providing communication between the communication terminal and the voice recognition server.

6. The communication terminal according to claim 5, further comprising:

a voice signal receiving means for receiving a second voice signal from the voice recognition server;

a sound producing means for producing a test sound based on the second voice signal;

a sound receiving means for receiving the test sound and for producing a loop back voice signal based on the received test sound;

a voice signal transmitting means for transmitting the loop back voice signal to the voice recognition server;

an adjustment data receiving means for receiving an adjustment data from the voice recognition server, the adjustment data is produced by analyzing the loop back voice signal and represents a sound characteristic of the communication network; and

an adjustment means for adjusting the sound characteristic of the communication network based on the adjustment data received from the voice recognition server by the adjustment data receiving means.

7. A voice recognition server used in a voice recognition system having a communication terminal which sends a voice signal via a communication network, for recognizing the voice signal received from the communication terminal, comprising:

a voice signal transmitting means for transmitting a second voice signal to the communication terminal;

a loop back signal receiving means for receiving a loop back voice signal that is the second voice signal produced and received by the communication terminal;

an adjustment data producing means for producing an adjustment data of a sound characteristic of the communication network, the adjustment data is produced by analyzing the loop back voice signal received from the communication terminal; and

an adjustment data transmitting means for transmitting the adjustment data produced by the adjustment data producing means to the communication terminal.

8. A computer program that is run by a communication terminal used in a voice recognition system, for sending a voice signal to a voice recognition server via a communication network, the voice recognition server recognizes the voice signal received from the communication terminal, to carry out:

a process of receiving a second voice signal from the voice recognition server;

a process of producing a test sound based on the second voice signal received from the voice recognition server;

a process of receiving the test sound and producing a loop back voice signal based on the received test sound;

a process of transmitting the loop back voice signal to the voice recognition server;

a process of receiving an adjustment data from the voice recognition server, the adjustment data is produced by analyzing the loop back voice signal and represents a sound characteristic of the communication network; and

a process of adjusting the sound characteristic of the communication network based on the adjustment data received from the voice recognition server.

9. A computer program which is run by a voice recognition server used in a voice recognition system, for recognizing a voice signal received from a communication terminal via a communication network, the communication terminal sends the voice signal to the voice recognition server, to carry out:

a process of transmitting a second voice signal to the communication terminal;

a process of receiving a loop back voice signal that is the second voice signal produced and received by the communication terminal,

a process of producing an adjustment data of a sound characteristic of the communication network, the adjustment data is produced by analyzing the loop back voice signal received from the communication terminal; and

a process of transmitting the adjustment data to the communication terminal.

10. In a voice recognition system having a communication terminal and a voice recognition server, a method for recognizing a voice signal comprising:

at the communication terminal, determining a sound characteristic of the communication channel between the communication terminal and the voice recognition server;

at the communication terminal, adjusting a received voice signal based on the determined sound characteristic;

at the communication terminal, sending the adjusted voice signal to the voice recognition server through the communication network; and

at the voice recognition server, recognizing the voice signal received from the communication terminal.