Looking for breakthrough ideas for innovation challenges? Try Patsnap Eureka!

Method, system and equipment for outputting sound source by microphone array and storage medium

A microphone array, sound source technology, applied in the direction of microphone signal combination, transducer circuit, sensor, etc., can solve the problem that audio data cannot be used directly

Active Publication Date: 2019-07-19
BEIJING JINGDONG SHANGKE INFORMATION TECH CO LTD +1
View PDF5 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] The technical problem to be solved by the present invention is to overcome the defect in the prior art that the multiple audio data of multiple sound sources output by the open source project of the microphone array cannot be directly used in the embedded device with limited resources, and provide a method suitable for resource Method, system, device and storage medium for outputting sound source by microphone array of limited embedded device

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 more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • Method, system and equipment for outputting sound source by microphone array and storage medium
  • Method, system and equipment for outputting sound source by microphone array and storage medium
  • Method, system and equipment for outputting sound source by microphone array and storage medium

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0074] Such as figure 1 As shown, the present embodiment provides a method for outputting a sound source by a microphone array, the sound source is multiple, and the method includes the following steps:

[0075] Step 101. Obtain the spectrum data of the current frame of each sound source, the current frame includes several frequency points, and the number of frequency points in this embodiment is 128;

[0076] Step 102, respectively calculating the energy of each frequency point of the current frame of each of the sound sources;

[0077] Step 103, respectively calculating the energy sum of all frequency points of the current frame of each of the sound sources according to the energy of each frequency point;

[0078] Step 104, comparing the energy sum of all the sound sources, and determining the sound source with the largest energy sum as the sound source to be output;

[0079] Step 105, output the frequency spectrum data of the current frame of the sound source to be output...

Embodiment 2

[0083] Such as figure 2 As shown, the present embodiment provides a method for outputting a sound source by a microphone array, the sound source is multiple, and the method includes the following steps:

[0084] Step 200, setting the value of the parameter preset time window;

[0085] Step 201, using ManyEars to obtain the spectrum data of each frame of each sound source, each frame includes M frequency points, M is a positive integer, and M is 512 in this embodiment;

[0086] Step 202, respectively calculate the energy of each frequency point of each frame of each of the sound sources, the calculation formula is:

[0087] power ik =real ik *real ik +imag ik *imag ik ;

[0088] Among them, i represents the i-th sound source, k represents the k-th frequency point, 0ik Represents the real part of the kth frequency point of the spectrum data of the current frame of the i-th sound source, imag ik Represents the imaginary part of the kth frequency point of the spectrum dat...

Embodiment 3

[0103] Such as image 3 As shown, this embodiment provides a system for microphone array output sound source, the sound source is multiple, and the system includes: acquisition module 1, first calculation module 2, first comparison module 3 and output module 4 .

[0104] The acquisition module 1 is used to acquire the frequency spectrum data of the current frame of each of the sound sources, and the current frame includes several frequency points.

[0105] The first calculation module 2 includes a second calculation module 21 and a third calculation module 22, the second calculation module 21 is used to calculate the energy of each frequency point of the current frame of each of the sound sources respectively; The third calculation module 22 is configured to separately calculate the energy sum of all frequency points of the current frame of each of the sound sources according to the energy of each frequency point.

[0106] The first comparison module 3 is used for comparing ...

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

No PUM Login to View More

Abstract

The invention discloses a method, a system and equipment for outputting sound sources by a microphone array and a storage medium. The number of the sound sources is multiple, and the method comprisesthe following steps: obtaining the frequency spectrum data of each sound source; respectively calculating the energy sum of each sound source according to the frequency spectrum data; comparing the energy sum of all the sound sources, and determining the sound source with the maximum energy sum as a to-be-output sound source; and outputting the spectrum data of the to-be-output sound source. According to the method, the system and the equipment for outputting the sound source by the microphone array, and the storage medium provided by the invention, the energy sum of the spectrum data of eachsound source is calculated, and then the determined energy and the maximum sound source are compared to serve as a final sound source to be output to be output. Therefore, a solution of one-way audioinput is provided for some embedded devices with limited resources, and the problem that in the prior art, a plurality of audio data of multiple sound sources output for an open source project of a microphone array cannot be directly used in the embedded devices with limited resources is solved.

Description

technical field [0001] The invention relates to the field of microphone array output control, in particular to a method, system, device and storage medium for microphone array output sound source. Background technique [0002] Microphone array-related technologies include sound source localization, tracking, separation, and post-filtering. At present, there are relatively mature open source projects that can track and separate multiple sound sources. After post-filtering, each sound source is separately The output is the corresponding audio file. For example, if there are 4 sound sources, 4 audio files will be output. [0003] If you need to use the output of an open source project for applications such as keyword recognition or speech recognition, you need to output it as an audio channel, or you need to multi-thread to process corresponding applications such as keyword recognition or speech recognition. In some embedded devices with limited resources, multi-threaded opera...

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
no application Login to View More
IPC IPC(8): H04R3/00
CPCH04R3/005
Inventor 杨楠
Owner BEIJING JINGDONG SHANGKE INFORMATION TECH CO LTD
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Patsnap Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Patsnap Eureka Blog
Learn More
PatSnap group products