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

Beam forming method based on deep learning and storage equipment

A deep learning and beam technology, applied in speech analysis, instruments, etc., can solve problems such as poor noise removal and inability to meet the needs of multiple people to pick up voices, and achieve accurate and intelligent recognition and judgment.

Pending Publication Date: 2021-08-13
FUZHOU ROCKCHIP SEMICON
View PDF0 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] To this end, it is necessary to provide a beamforming method based on deep learning to solve the problem that the existing adaptive microphone array beamforming technology is not effective in removing non-human noise and cannot meet the needs of multiple people speaking

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
  • Beam forming method based on deep learning and storage equipment
  • Beam forming method based on deep learning and storage equipment
  • Beam forming method based on deep learning and storage equipment

Examples

Experimental program
Comparison scheme
Effect test

specific Embodiment approach

[0036] see Figure 1 to Figure 5 , in this embodiment, a beamforming method based on deep learning can be applied to a storage device, the storage device includes but not limited to: personal computer, server, general-purpose computer, special-purpose computer, network equipment, embedded devices, programmable devices, smart mobile terminals, etc. The specific implementation is as follows:

[0037] The technical thought of this application is described below with application in the meeting:

[0038] When the application scenario is a conference, the core technical idea of ​​this application lies in: because in the conference application scenario, human voices are the main ones, the beamforming should preferentially point to the voice direction of people, and at the same time, when there are many people talking in the conference, the beamforming Cannot be single beam. Therefore, this application has mainly made two improvements: one is to introduce deep learning technology, ...

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 relates to the technical field of beam processing, in particular to a beam forming method based on deep learning and storage equipment. The beam forming method based on deep learning. The method comprises the steps that acquired voice data are processed through a deep learning technology to obtain human voice and non-human voice noise, so that compared with a traditional adaptive beam forming algorithm, recognition and judgment of the human voice and the non-human voice noise are more accurate and intelligent; and in the recognized human voice direction, signal energy detection is carried out, and weighted superposition calculation is carried out on the beam size according to an energy detection result, so that the human voice can be picked up in multiple directions at the same time, and the pickup requirement of multi-person speaking in a conference scene or any other scene is met.

Description

technical field [0001] The present invention relates to the technical field of beam processing, in particular to a deep learning-based beamforming method and a storage device. Background technique [0002] In conventional adaptive microphone array beamforming techniques, such as super-directional beams, noise is suppressed by minimizing scattered noise while keeping the direction-of-arrival output constant. However, such methods often need to know the direction of arrival in advance, and the correlated noise of human voice often leads to inaccurate estimation of the direction of arrival, thus affecting the beam effect. [0003] In actual meeting scenarios, there is often a need for multiple people to speak, and if the existing adaptive microphone array beamforming technology is used, the direction of arrival of the wave cannot be known in advance, resulting in the inability to remove noise well, affecting the The beam effect makes it impossible to meet the sound pickup requ...

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
Patent Type & Authority Applications(China)
IPC IPC(8): G10L21/0216G10L21/0264G10L25/30
CPCG10L21/0216G10L25/30G10L21/0264G10L2021/02166
Inventor 李茂发江正梁陈时钦
Owner FUZHOU ROCKCHIP SEMICON
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

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic, Popular Technical Reports.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com