Sound source direction estimation method and device

Abstract

The invention discloses a sound source direction estimation method and device. The method comprises the steps of collecting an image through a camera when a sound signal is detected; obtaining position coordinates of a sound source in the image; calculating a first included angle between a connecting line of the camera and the sound source and a projection surface of the camera according to the position coordinates; and calculating the direction of the sound source according to the first included angle and a preset second included angle, wherein the second included angle is an angle between aconnecting line of two microphones and a horizontal axis of the camera. The position coordinates of the sound source in the image are obtained by using an image recognition technology, and the direction of the sound source is estimated accordingly, thereby avoiding influences imposed on sound source direction estimation by environmental noise, improving the accuracy of sound source direction estimation, and thus laying a foundation for improving the effect of subsequent voice noise reduction or sound source positioning.

Description

technical field

[0001] The present invention relates to the field of electronic technology, in particular to a sound source direction estimation method and device. Background technique

[0002] In application scenarios such as speech noise reduction and sound source tracking, it is necessary to first estimate the direction of the sound source. At present, the most effective sound source direction estimation method is to use dual-microphone technology for sound source direction estimation, that is, two microphones are used to collect sound signals, and the sound source direction is estimated according to the phase difference of the two collected sound signals.

[0003] However, when it is used for far-field speech noise reduction, or when the background noise is large, the effect of the above-mentioned sound source direction estimation method will be greatly reduced, resulting in an inaccurate estimated sound source direction, which will affect subsequent speech noise reducti...

Examples

no. 1 example

[0096] refer to figure 1 , propose the first embodiment of the sound source direction estimation method of the present invention, the method includes the following steps:

[0097] S11. When the sound signal is detected, collect an image through the camera.

[0098] In the embodiment of the present invention, the terminal device detects sound through dual microphones, and immediately collects an image through a camera when a sound signal is detected.

[0099] S12. Acquire the position coordinates of the sound source in the image.

[0100] In the embodiment of the present invention, the terminal device uses face recognition technology to recognize the face in the image, and when the face is recognized, it obtains the position coordinates of the lips of the face in the image, and uses the position coordinates of the lips as the sound source in the image The location coordinates in .

[0101] Optionally, when there are at least two human faces in the image, detect whether the l...

technical field

[0001] The present invention relates to the field of electronic technology, in particular to a sound source direction estimation method and device. Background technique

[0002] In application scenarios such as speech noise reduction and sound source tracking, it is necessary to first estimate the direction of the sound source. At present, the most effective sound source direction estimation method is to use dual-microphone technology for sound source direction estimation, that is, two microphones are used to collect sound signals, and the sound source direction is estimated according to the phase difference of the two collected sound signals.

[0003] However, when it is used for far-field speech noise reduction, or when the background noise is large, the effect of the above-mentioned sound source direction estimation method will be greatly reduced, resulting in an inaccurate estimated sound source direction, which will affect subsequent speech noise reducti...

Examples

no. 1 example

[0096] refer to figure 1 , propose the first embodiment of the sound source direction estimation method of the present invention, the method includes the following steps:

[0097] S11. When the sound signal is detected, collect an image through the camera.

[0098] In the embodiment of the present invention, the terminal device detects sound through dual microphones, and immediately collects an image through a camera when a sound signal is detected.

[0099] S12. Acquire the position coordinates of the sound source in the image.

[0100] In the embodiment of the present invention, the terminal device uses face recognition technology to recognize the face in the image, and when the face is recognized, it obtains the position coordinates of the lips of the face in the image, and uses the position coordinates of the lips as the sound source in the image The location coordinates in .

[0101] Optionally, when there are at least two human faces in the image, detect whether the l...

Images