SOUND SOURCE DETECTION SYSTEM

• US 20140241126A1
• Filed: 09/19/2012
• Published: 08/28/2014
• Est. Priority Date: 09/20/2011
• Status: Active Grant

• Current Assignee: Meijo University, Toyota Jidosha Kabushiki Kaisha (Toyota Motor Corporation)
• Original Assignee: Meijo University, Toyota Jidosha Kabushiki Kaisha (Toyota Motor Corporation)
• Inventors: Funayama, Ryuji, Sato, Jun, Yamamoto, Osami, Asahi, Kensaku, Banno, Hideki, Ogawa, Akira, Tanaka, Yuichi, Yamada, Keiichi, Hoshino, Hiroyuki
• Granted Patent: US 9,091,751 B2
• Time in Patent Office: Days
• US Class Current: 367/129
• CPC Class Codes: G01S 11/14 using ultrasonic, sonic, or infrasonic waves
• CPC Class Codes: G01S 3/808 using transducers spaced apart and measuring phase or time difference between signals therefrom, i.e. path-difference systems

Abstract

A sound source detection system for detecting a sound source (e.g., running sound of a vehicle) based on sound collected by microphones extracts characteristic amounts from the sound collected by the microphones, sets a plurality of classes according to the position of the sound source by a multi-class pattern recognition method (e.g., multi-class SVM) using the characteristic amounts, extracts characteristic amounts from sound collected by the microphones for detection of a sound source, determines a class to which the extracted characteristic amounts belong, from the preset plurality of classes, and estimates the sound source based on the class.

Claims

1. A sound source detection system for detecting a sound source based on sound collected by a sound collecting device, comprising:

a classifying unit configured to extract a plurality of characteristic amounts from the sound collected by the sound collecting device, and to set a plurality of classes according to a position of the sound source by a multi-class pattern recognition method, using the characteristic amounts;

a class determining unit configured to extract the characteristic amounts from the sound collected by the sound collecting device when detecting the sound source, and to determine a class to which the extracted characteristic amounts belong, from the plurality of classes set by the classifying unit; and

a sound source estimating unit configured to estimate the sound source, based on the class determined by the class determining unit.

2. The sound source detection system according to claim 1, further comprising:

a sound source detecting unit configured to calculate a correlation value of sounds respectively collected by a plurality of microphones that constitute the sound collecting device, and to detect the sound source by comparing the calculated correlation value with a threshold value; and

a correcting unit configured to correct the threshold value of the sound source detecting unit, based on a detection result obtained by the sound source detecting unit and an estimation result obtained by the sound source estimating unit, wherein

the sound source detecting unit detects the sound source by comparing the correlation value with the threshold value corrected by the correcting unit.

3. The sound source detection system according to claim 2, wherein:

the sound source estimating unit estimates a distance to the sound source, and the sound source detecting unit calculates a distance to the sound source, and

the correcting unit corrects the threshold value of the sound source detecting unit by setting the threshold value to a smaller value, when the sound source estimating unit and the sound source detecting unit detect the sound source, and the distance to the sound source estimated by the sound source estimating unit is approximately equal to the distance to the sound source calculated by the sound source detecting unit.

4. The sound source detection system according to claim 1 wherein:

the sound collecting device includes at least one pair of microphones; and

the plurality of characteristic amounts include a delay of arrival of sound and a correlation value, which are extracted from each of the at least one pair of microphones.

5. The sound source detection system according to claim 1, wherein the classifying unit sets the plurality of classes according to a length of time it takes for the sound source to reach a reference point in time.

6. The sound source detection system according to claim 1, wherein the classifying unit sets the plurality of classes according to a moving direction of the sound source.

7. The sound source detection system according to claim 1, wherein:

the sound source is a vehicle approaching a self-vehicle on which the sound source detection system is installed; and

the classifying unit sets the plurality of classes according to a shape of a road on which the vehicle is running and a shape of a road on which the self-vehicle is present.

8. The sound source detecting system according to claim 1, wherein:

the sound source is a vehicle approaching a self-vehicle on which the sound source detection system is installed; and

the classifying unit sets the plurality of classes according to traffic regulations for a road on which the vehicle is running and a road on which the self-vehicle is present.

9. The sound source detection system according to claim 1, wherein:

the sound source is a vehicle approaching a self-vehicle on which the sound source detection system is installed; and

the classifying unit sets the plurality of classes according to a type of the approaching vehicle.