Audio input device and method of controlling the same

• US 7,047,198 B2
• Filed: 10/09/2001
• Issued: 05/16/2006
• Est. Priority Date: 10/11/2000
• Status: Expired due to Fees

• Current Assignee: Nissan Motor Co., Ltd.
• Original Assignee: Nissan Motor Co., Ltd.
• Inventors: Ono, Takeshi, Nakayama, Okihiko
• Primary Examiner(s): McFadden, Susan
• Assistant Examiner(s): Jackson, Jakieda R.
• Application Number:
  US09/971,698
• Publication Number:
  US 20020059067A1
• Time in Patent Office: 1,680 Days
• Field of Search: 704/275, 455/419, 455/569, 743/35, 701/202, 340/999, 340/905, 304/439, 364/424.051, 342/357.07
• US Class Current: 704/275
• CPC Class Codes: G10L 15/22 Procedures used during a speech recognition process, e.g. man-machine dialogue

Abstract

An audio input device calculates respective degrees of coincidence between a user'"'"'s vocalizations and recognition terms in a voice dictionary by speech recognition and extracts a recognition term having the highest degree of coincidence from the voice dictionary. Further, the audio input device outputs a command to operate one of installations, such as radio, CD player, air conditioner, etc. The audio input device includes a remote controller for transmitting signal waves to the installations equipped with receivers to carry out remote control of the installations. In operation, the larger the installation which the remote controller is directed to has a receiving intensity of the signal wave detected byte receiver, the larger the audio input device makes an extraction weight of the recognition terms concerned with the installation, in the voice dictionary.

Claims

1. An audio input device comprising:

a plurality of installations to be operated;

a pickup unit for picking up vocalizations of a user;

a speech dictionary for storing objective recognition terms corresponding to the operations of the installations, the objective recognition term being classified with extraction weight for every installation;

a remote controller operated by the user to transmit a signal wave to each of the installations to carry out remote control of the installations; and

a controller connected to the installations, the pickup unit and the speech dictionary, the controller having;

a calculating section for calculating respective degrees of coincidence between the user'"'"'s vocalizations inputted through the pickup unit and the objective recognition terms in the speech dictionary;

an extracting section for extracting the objective term having the highest degree of coincidence, from the speech dictionary;

an operating section for generating an operation command to one of the installations on the ground of an extraction result transmitted from the extracting section; and

an estimating section for estimating the installation at which the remote controller is pointed by the user,

wherein, at the calculation of the degrees of coincidence on receipt of the user'"'"'s vocalizations, the controller makes the extraction weight of the objective recognition terms concerned with the installation estimated by the estimating Section, larger than the extraction weight of the objective recognition terms concerned with the other installation.

2. The audio input device of claim 1, wherein

the estimating section has a receiving-intensity detecting part the signal wave transmitted from the remote controller to detect a receiving intensity of the signal wave received;

and

the larger the installation has a receiving intensity of the signal wave detected by the receiving-intensity detecting part, the larger the extracting section makes the extraction weight of the objective recognition terms concerned with the installation.

3. The audio input device of claim 1, wherein the estimating section has a position-and-direction detecting unit for detecting both three-dimensional position and direction of the remote controller.

4. The audio input device of claim 3, wherein the position-and-direction detecting unit includes:

at least two ultrasonic transmitters arranged in the remote controller;

at least three ultrasonic receivers arranged in the circumference of the remote controller, the ultrasonic receiver receiving the ultrasonic waves transmitted from the ultrasonic transmitter; and

an ultrasonic transmitter detecting part for detecting respective three-dimensional positions of the ultrasonic transmitters on a basis of the times from the transmission of ultrasonic waves by the ultrasonic transmitters to the arrival of ultrasonic waves at the ultrasonic receivers.

5. The audio input device of any one of claim 1, wherein the installations are installed in a vehicle compartment.

6. The audio input device of claim 5, further comprising a driving-load detecting unit for detecting a driving load on a driver who drives the vehicle.

7. The audio input device of claim 6, wherein the driving-load detecting unit has a driving-load detecting part for detecting a busyness of driving the vehicle, and the driving-load detecting unit outputs the command signal to enlarge the irradiation area of the signal wave transmitted from the remote controller when the driving load detected by the driving-load detecting part is more than a predetermined value.

8. The audio input device of claim 6, wherein the driving-load detecting unit has an attentiveness-necessity detecting part for detecting a necessity of the driver'"'"'s attentiveness in driving the vehicle, and the driving-load detecting unit outputs the command signal to enlarge an irradiation area of the signal wave transmitted from the remote control when the necessity of attentiveness detected by the attentive-necessity detecting part is more than a predetermined value.

9. The audio input device of claim 1, wherein the controller re-extracts extracts the objective recognition term having the highest degree of coincidence from the speech dictionary when the direction of the remote controller is after the objective recognition term having the highest degree of coincidence has been extracted by the extracting section.

10. The method of claim 1, further comprising when the direction of the remote controller is changed after the objective recognition term having the highest degree of coincidence has been extracted by the extracting section,

re-calculating respective degrees of coincidence between the vocalizations inputted through the pickup unit and the objective recognition terms in the speech dictionary;

and

re-extracting an objective recognition term having the highest degree of coincidence, from the speech dictionary.

11. An audio input device comprising:

a plurality of installations to be operated;

a pickup unit for picking up vocalizations of a user;

a speech dictionary for storing objective recognition terms corresponding to the operations of the installations, the objective recognition term being classified with extraction weight for every installation;

means for calculating respective degrees of coincidence between the vocalizations inputted through the pickup unit and the objective recognition terms in the speech dictionary

means for extracting an objective recognition term having the highest degree of coincidence, from the speech dictionary;

means for operating one of the installations on the ground of an extraction result transmitted from the extracting section;

a remote controller operated by the user to transmit a signal wave to each of the installations to carry out remote control of the of the installations; and

means for estimating the installation at which the remote controller is pointed by the user;

wherein, at the calculation on receipt of the user'"'"'s vocalizations, the extraction weight of the objective recognition terms concerned with the installation estimated by the estimating means is established larger than the extraction weight of the objective recognition terms concerned with the other installation.

12. A method of controlling an audio input device having a plurality of installations to be operated, a pickup unit for picking up vocalizations of a user, a speech dictionary for storing objective recognition terms corresponding to the operations of the installations, the objective recognition term being classified with extraction weight for every installation, and a remote controller operated by tile user to carry out remote control of the installations by transmitting a signal wave to each of the installations, the method comprising:

calculating respective decrees of coincidence between the vocalizations inputted through the pickup unit and the objective recognition terms in the speech dictionary;

estimating the installation at which the remote controller is pointed by the user;

extracting an objective recognition term having the highest degree of coincidence, from the speech dictionary; and

operating one of the installations on the ground of a result of the extracting operation;

wherein, at the calculating operation, the extraction weight of the objective recognition terms concerned with the installation estimated by the estimating operation as established larger than the extraction weight of the objective recognition terms concerned with the other installation.