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

Classifying method for aliasing audio events

A classification method and audio technology, applied in speech analysis, speech recognition, instruments, etc., can solve the problem of failing to recognize multiple audio events of aliased audio

Inactive Publication Date: 2015-01-07
SHANDONG NORMAL UNIV
View PDF5 Cites 12 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, the current research on aliasing audio in the audio field mainly focuses on the field of speech recognition, and there are few studies on aliasing of different types of audio events, and the existing research fails to identify multiple audio events in aliasing audio.
This is mainly due to the variety of aliasing types of aliased audio events, which poses a great challenge to the classification strategy of aliased audio events

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
  • Classifying method for aliasing audio events
  • Classifying method for aliasing audio events
  • Classifying method for aliasing audio events

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0072] The present invention will be further described below in conjunction with the accompanying drawings and embodiments.

[0073] In order to solve the classification problem of aliasing audio events, this application proposes to classify based on the "author-topic" model and the "topic-word" model. Here, the author of the audio document refers to the audio event contained in the audio document. For example, if an audio file is formed by mixing speech and music, the author of the audio file is the speech and music. The word of the audio document refers to constructing a dictionary with a text-like processing method on the audio document set, and then using the words in the dictionary to express each audio event sample. The aliasing audio event classification method based on the "author-topic" model and "topic-word" model is divided into two stages: training and testing. Both the training phase and the testing phase are figure 1 As shown, the ultimate goal of the training...

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 classifying method for aliasing audio events. According to the method, an author-subject model theta and a subject-word model phi are obtained through a Gibbs sampling method in the training stage. In the testing stage, according to the author-subject model theta and the subject-word model phi obtained in the training stage, aliasing audio events are classified by solving uncertainty values of audio documents relative to aliasing audio classes. The classifying method for aliasing audio events can classify and recognize multiple audio events in audio samples, not just a certain audio event, so that content of audio documents is analyzed better. Currently, research on classification of aliasing audio events is little, and the classifying method is a good supplement of the research on classification of aliasing audio events.

Description

technical field [0001] The invention relates to a method for classifying audio events, in particular to a method for classifying aliasing audio events. Background technique [0002] Audio event classification is an important research topic in computational auditory scene analysis. Audio events can provide us with a wealth of information. For example, the sound of speech can make people understand the current conversation content, the sound of music can help people analyze the current environment they are in, and the applause in the conference room can make people understand the progress of the current meeting, etc. Wait. [0003] Audio events contained in audio files can generally be divided into two types, one is pure audio events, that is, only one audio event occurs at the same time; the other is aliased audio events, that is, multiple audio events occur at the same time occur. [0004] The current classification technology has been able to classify pure audio events v...

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): G10L15/08G10L25/51G10L15/06
Inventor 冷严程传福齐广慧徐新艳万洪林
Owner SHANDONG NORMAL UNIV
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