Method and equipment for classifying audio signals in real time

An audio signal and classification method technology, applied in the field of audio codec and transmission, can solve the problems of low practicability and long processing time, and achieve the effect of improving the efficiency of audio codec and improving the accuracy of real-time classification

Inactive Publication Date: 2012-07-04
NANJING UNIV
View PDF2 Cites 26 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Due to the relatively long processing time, these methods are not very practical for real-time audio classification

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 and equipment for classifying audio signals in real time
  • Method and equipment for classifying audio signals in real time
  • Method and equipment for classifying audio signals in real time

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0038] The main idea of ​​the present invention is, can adopt a kind of real-time audio signal classification method to carry out the speech audio signal category decision before encoding (as figure 1 ), on this basis, select an encoder suitable for speech or audio according to similar judgments, so as to improve the encoding efficiency of speech and audio codecs for different types of signals. The specific process is as follows:

[0039] Step 1, signal framing and high-pass filter processing, filter out unnecessary low-frequency signals; silence detection, use the short-term zero-crossing rate to perform current frame silence detection, when the short-time zero-crossing rate of the current frame is greater than the first setting Value, set the current frame as a non-silent frame. ;

[0040] Step 2, MDCT transformation, extract a series of audio features in the time domain and MDCT domain, audio features include short-term zero-crossing rate, MDCT spectrum harmonic structure ...

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 and equipment for classifying audio signals in real time, belonging to the technical field of audio encoding and decoding. The method comprises the following steps: preprocessing the inputted audio signals; extracting multi-level audio features in a time domain and an MDCT domain; classifying a current frame by adopting the signal audio feature if the current frame is in a classification convergence time frame I; classifying the current frame by adopting the coarse-fine classification rule if the current frame is behind the classification convergence time frame I, and judging classification features by adopting the multi-level features; and after classifying the current frame by adopting the coarse-fine classification rule, upgrading the signal classification type of the current frame according to the historical state of the classification type of a signal frame before the current frame. Due to the adoption of the method and the equipment, the signals can be classified in real time simply and accurately.

Description

1. Technical field [0001] The invention relates to the field of audio codec and transmission, in particular to a real-time audio signal classification method and equipment. 2. Background technology [0002] Classification of audio signals before encoding, transmission or other processing can effectively improve the efficiency of encoding and transmission. Since the transmission of multimedia audio signals is based on the framework of real-time transmission, the real-time classification of audio signals is a important research content. [0003] Most of the research on audio signal classification at home and abroad focuses on long-term classification, such as low-energy rate classification of 1 second or 10 seconds and short-term energy classification of 1 second or 10 seconds. Statistical classification methods are generally used in the design of classifiers, such as support vector machine classifiers, neural network classifiers, etc. Due to the relatively long processing t...

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): G10L15/08G10L15/02
Inventor 林志斌孔庆胜
Owner NANJING UNIV
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products

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

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap