A sound source localization method and device based on image recognition and speech recognition
A voice recognition and image recognition technology, applied in voice analysis, measuring devices, optical devices, etc., can solve problems such as inability to accurately locate sound sources, and achieve the effect of high practicability and precise positioning
Active Publication Date: 2021-06-18
AISPEECH CO LTD
View PDF17 Cites 0 Cited by
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
[0003] In order to solve the above problems, the inventor conceived by referring to the principle of bionics (it is a border science intersecting biological science and technical science, its task is to apply the excellent ability and function of the biological system to the development of technology, so as to better Solve technical problems), apply image recognition technology combined with voice recognition technology to achieve precise positioning of the direction of the sound source, so that it can solve the problem that the sound source cannot be precisely positioned by relying solely on the microphone array
Method used
the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View moreImage
Smart Image Click on the blue labels to locate them in the text.
Smart ImageViewing Examples
Examples
Experimental program
Comparison scheme
Effect test
Embodiment Construction
[0017] In order to make the purpose, technical solutions and advantages of the embodiments of the present invention clearer, the technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments It is a part of embodiments of the present invention, but not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by persons of ordinary skill in the art without making creative efforts belong to the protection scope of the present invention.
[0018] It should be noted that, in the case of no conflict, the embodiments in the present application and the features in the embodiments can be combined with each other.
[0019] The invention may be described in the general context of computer-executable instructions, such as program modules, being executed by a computer. Generally, progr...
the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More PUM
Login to View More Abstract
The invention discloses a sound source localization method based on image recognition and voice recognition, comprising: capturing image information in real time, performing image recognition, and determining the first coordinate position according to the image recognition result; collecting sound source information in real time, performing voice recognition, and The second coordinate position is determined according to the speech recognition result; the target sound source position is determined according to the first coordinate position and the second coordinate position. The invention also discloses a sound source localization device based on image recognition and speech recognition. According to the method and device disclosed in the invention, the precise positioning of the direction and position of the sound source can be realized through the image recognition technology and the microphone array, and can also be achieved through The image recognition technology and the distance measurement of the direction and position of the sound source by the microphone array can achieve a more accurate positioning effect and have higher practicability.
Description
technical field [0001] The invention relates to the technical field of speech recognition and image recognition, in particular to a sound source localization method and device based on image recognition and speech recognition. Background technique [0002] With the development of science and technology, smart devices are becoming more and more popular. Among them, sound source positioning is particularly important for some smart devices. At present, the market relies solely on microphone arrays to locate sound sources, which often leads to inaccurate results, and There are very high requirements for the accuracy of the algorithm, layout, and test angle of the microphone array. Basically, the accuracy requirements for positioning cannot be achieved, that is, accurate positioning cannot be achieved. This will lead to the positioning of the direction of the sound source through a simple microphone array, which cannot be applied in practice, or the application effect is very poo...
Claims
the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More Application Information
Patent Timeline
Login to View More Patent Type & AuthorityPatents(China)
IPC IPC(8): G01B11/00G01S11/14G10L17/00G10L25/51
CPCG01B11/002G01S11/14G10L17/00G10L25/51
Inventor雷玉雄雷雄国刘寒英黄海艳程栋梁曾勋陈庆安
OwnerAISPEECH CO LTD