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

A Classification Method Based on Audio Feature Signal

An audio signal and audio feature technology, applied in the field of classification based on audio feature signals, can solve problems such as complex algorithms, large amount of calculation, and poor classification effect, and achieve the effect of simple principle, easy programming, and strong robustness

Active Publication Date: 2022-07-19
KUNMING UNIV OF SCI & TECH
View PDF0 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0002] In order to improve the recognition efficiency and accuracy based on audio signals, and the audio feature classification also plays a decisive role in the audio monitoring control of wireless broadcasting, the research on the classification algorithm based on audio feature signals is particularly important, and the current The main classification algorithms include Bayesian classification algorithm, decision tree algorithm, support vector machine algorithm, etc. For these classification algorithms, most of them have poor classification effect, complex algorithm, large amount of calculation, and difficult to implement programming, etc.

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
  • A Classification Method Based on Audio Feature Signal
  • A Classification Method Based on Audio Feature Signal
  • A Classification Method Based on Audio Feature Signal

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0048] The present invention will be further described below in conjunction with the accompanying drawings and embodiments.

[0049] like figure 1 As shown, a classification method based on audio feature signal, the specific steps are as follows:

[0050] (1) Audio signal collection: collect audio signals to obtain audio samples.

[0051] (2) Audio signal preprocessing: convert the analog signals in the collected audio samples into digital signals, and write the digital signals into a WAV file. Filter and frame the digital signal to be written into the WAV file.

[0052] (3) Feature parameter extraction: The programming realizes the extraction of high-dimensional feature parameters of linear prediction coefficient (LPC), linear prediction cepstral coefficient (LPCC) and Mel frequency cepstral coefficient (MFCC) for the preprocessed audio signal.

[0053] (4) Dimensionality reduction of feature parameters: The audio feature parameters extracted above are sent into the built ...

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 a classification method based on an audio characteristic signal, and belongs to the technical field of audio signal processing. The present invention classifies the audio feature signal after dimensionality reduction processing by using Gaussian kernel function and Bayesian prior knowledge. The classification algorithm based on the audio feature signal of the present invention can be used for audio broadcast monitoring, artificial intelligence speech recognition, audio scene mode distinction, and the like. The present invention mainly performs audio classification based on the coefficient domain feature of the audio characteristic signal, and is more universal and stable compared with the prior art of classifying based on audio content. The invention utilizes the excellent nonlinear characteristics of the Gaussian kernel function and the efficient optimization algorithm, thereby avoiding the shortcomings of single application scene, slow running speed and poor classification effect caused by the use of linear mapping. The algorithm theory is also relatively simple and easy to program and implement, which is more practical and practical in engineering projects.

Description

technical field [0001] The invention relates to a classification method based on audio feature signals, and belongs to the technical field of audio feature signal processing. Background technique [0002] In order to improve the recognition efficiency and accuracy based on audio signals, and audio feature classification also plays an important role in the audio monitoring control of wireless broadcasting, it is particularly important to study the classification algorithm based on audio feature signals. The main classification algorithms include Bayesian classification algorithm, decision tree algorithm, support vector machine algorithm, etc. Most of these classification algorithms have poor classification effect, complex algorithm, large amount of calculation, and difficult programming. This algorithm utilizes the excellent nonlinear characteristics of the Gaussian kernel function and combines the Bayesian prior theory, and can achieve satisfactory results in the classificat...

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 Patents(China)
IPC IPC(8): G10L25/24G10L25/00G10L15/22G10L15/18G10L15/08
CPCG10L15/08G10L15/18G10L15/22G10L25/00G10L25/24
Inventor 龙华杨明亮邵玉斌杜庆治
Owner KUNMING UNIV OF SCI & 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