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

Audio scene classification method, device and equipment applied to audio monitoring

A scene classification and audio technology, applied in speech analysis, instruments, etc., can solve the problems of time-consuming and resource-consuming, and achieve the effect of reducing the detection burden and improving the processing time.

Pending Publication Date: 2021-03-26
IFLYTEK CO LTD
View PDF0 Cites 2 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0005] In view of the above, the present invention aims to provide an audio scene classification method, device and equipment applied to audio monitoring, and accordingly provides a computer-readable storage medium and a computer program product, which can effectively solve the problems required in the field of audio monitoring Scene classification deals with time-consuming and resource-intensive problems

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
  • Audio scene classification method, device and equipment applied to audio monitoring
  • Audio scene classification method, device and equipment applied to audio monitoring
  • Audio scene classification method, device and equipment applied to audio monitoring

Examples

Experimental program
Comparison scheme
Effect test

Embodiment approach

[0108] It is integrated the above examples and the preferred embodiments, and those skilled in the art will appreciate that in practice, the technical concepts according to the present invention can be applied to a variety of embodiments, and the following carriers are shown as schematic description:

[0109] (1) A audio scene classification device applied to audio monitors. The apparatus can specifically include: one or more processors, memory, and one or more computer programs, wherein the one or more computer programs are stored in the memory, the one or more computer programs including instructions. When the instruction is performed by the device, the device performs the step / function of the foregoing embodiment or equivalent embodiment.

[0110] Figure 4 A schematic structural diagram of an embodiment of an audio scene classification apparatus applied to audio monitors is provided in the present invention, wherein the device can be a server, a desktop PC, a laptop, a smart...

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 an audio scene classification method, device and equipment applied to audio monitoring, and aims to solve problems that an existing audio scene classification mode consumes time and wastes resources from two aspects, on one hand, quality research and judgment are carried out on each audio segment in real time on the basis of processing timeliness, and on the other hand, theaudio scene classification efficiency is improved; according to the method, only the effective audio clips are detected, the audio clips are taken as processing units, and processing of other available clips is stopped once the classification result is detected, so unnecessary detection processes can be greatly reduced; on the other hand, by utilizing the characteristics of the RNN architecture,the information of each audio clip does not need to be stored in the scene type detection process, and only the processing result of the previous step needs to be used as the input of subsequent processing, so the resource space can be fully saved; therefore, the method not only can guarantee the processing time efficiency, but also can enable the system to be light in weight, thereby being flexibly suitable for audio monitoring application environments of various scales.

Description

Technical field [0001] The present invention relates to the field of audio monitoring, and more particularly to an audio scenario classification method, apparatus, and apparatus for use in audio monitoring. Background technique [0002] After years of development in the field of audio monitoring, the role of the high-quality smart security system has highlighted its importance. Since the technical characteristics of the audio itself will not be interfered by the line of sight obstacles, the illumination is unfavorable, can make up for the insufficient visual, and provide a variety of information for the determination situation, and the function of video cannot be replaced. The audio scene analysis is mainly for analysis, decision-making, and anomalous behavior that occurs in the current listener environment. Its core technology is based on various types of abnormal audio, and the classification method of time domain, frequency domain, combined with the classification method ident...

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): G10L25/30G10L25/51
CPCG10L25/30G10L25/51
Inventor 黄真明陆春亮王毅
Owner IFLYTEK 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