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

Method for recognizing audio based on spectrogram significance test

An audio recognition and spectrogram technology, applied in speech analysis, instruments, etc., can solve the problem of unpractical audio data

Active Publication Date: 2015-05-13
HEFEI UNIV OF TECH
View PDF3 Cites 22 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, the boosting classifier relies too much on artificially setting and adjusting thresholds, and this method is not practical for identifying audio data of unknown audio types in complex environments

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 for recognizing audio based on spectrogram significance test
  • Method for recognizing audio based on spectrogram significance test
  • Method for recognizing audio based on spectrogram significance test

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0045] In this example, if figure 1 As shown, an audio recognition method based on spectrogram saliency detection is performed in the following steps:

[0046] Step 1. Obtain the spectrograms of n different sound sources with M×N pixels, and obtain m pieces of each kind of spectrogram, so as to obtain m×n spectrograms D={d 1 , d 2 ,...,d i ,...,d m×n}; d i Indicates the i-th spectrogram; i∈[1,m×n];

[0047] Carry out feature extraction respectively to m×n spectrogram D, obtain basic feature set; Basic feature set includes: RGBY chromaticity feature set C={C 1 ,C 2 ,...,C i ,...,C m×n}, direction feature set O={O 1 ,O 2 ,...,O i ,...,O m×n} and brightness feature set I={I 1 , I 2 ,...,I i ,...,I m×n};C i Indicates the i-th spectrogram d i RGBY chromaticity characteristics; O i Indicates the i-th spectrogram d i directional characteristics; I i Indicates the i-th spectrogram d i The brightness feature; in the present embodiment, the direction feature is rep...

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 for recognizing audio based on spectrogram significance test. The method is characterized by comprising the following steps: 1, acquiring spectrograms of different sound sources, and extracting characteristics to obtain a basic characteristics set; 2, obtaining a significance map by the GBVS algorithm, and extracting a main map by the main map separating method; 3, extracting a hierarchy correlation map; 4, acquiring a PCA characteristics map; 5, building GCNN sound source models of different sound sources; 6, recognizing the sound sources of which the spectrograms are to be tested according to the GCNN sound source models. With the adoption of the method, the characteristic information of unknown audio type under a complex environment can be effectively represented, and meanwhile, the audio can be quickly and automatically recognized.

Description

technical field [0001] The invention belongs to the field of audio recognition, in particular to an audio recognition method based on the significance detection of spectrogram. Background technique [0002] With the rapid development of the Internet, a large amount of audio, video and image information has emerged. However, the research speed of audio information is far behind the research of video and images, and the identification of a large amount of audio information is a huge and cumbersome project only by manual labeling. Therefore, to realize the automatic identification of audio signals, It is the focus of research in the field of audio. [0003] The existing automatic recognition methods of audio signals are mainly carried out through two steps of extracting features and selecting classifiers, among which the research and extraction of sound features of audio signals is a traditional and commonly used audio recognition method. However, for a large amount of unknow...

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): G10L25/03G10L25/48
Inventor 陈雁翔弓彦婷任洪梅王猛
Owner HEFEI UNIV OF TECH
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