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

MP3 compression field audio partitioning method

A compressed domain and audio technology, applied in speech analysis, speech recognition, special data processing applications, etc., to achieve the effect of simple algorithm, saving computing time, and eliminating adverse effects

Inactive Publication Date: 2008-07-16
SHANGHAI UNIV
View PDF0 Cites 24 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0003] Commonly used audio segmentation methods, most of the work is carried out in the uncompressed domain, and the problem of directly segmenting audio in the compressed domain and detecting speaker change points is rarely involved

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
  • MP3 compression field audio partitioning method
  • MP3 compression field audio partitioning method
  • MP3 compression field audio partitioning method

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0016] A preferred embodiment of the present invention is described as follows in conjunction with accompanying drawing: this MP3 compressed domain audio frequency segmentation method is divided into six steps altogether:

[0017] Step 1: MP3 compressed domain audio data processing

[0018] The processing of compressed domain audio data is divided into reading of frame header information, reading of side information, reading of main data, Huffman decoding and quantization.

[0019] 1. Reading of frame header information

[0020] A), define the structure layer that stores the frame header information;

[0021] B), read the synchronization information in the frame;

[0022] C), the decoder is synchronized with the data stream;

[0023] D), determine the position where the frame data starts, and store the frame header information in the variable Head of the layer type i middle.

[0024] 2. Reading side information

[0025] A), define the structure sideinf for storing side i...

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 an MP3 compressed domain audio segmentation method which extracts characteristic parameters from MP3 compressed audio data; then audio information is processed by mute segmentation; non-mute is processed by speech segmentation; speaker changing detection is carried out on a speed segment by a statistical decision model, finally a segmentation result is achieved by a speaker changing point. Through the experimental result, compared with the prior segmentation method, the segmentation method adopted by the invention has remarkable improvement on accuracy, recall ratio and comprehensive performance.

Description

technical field [0001] The invention relates to signal processing and pattern recognition, and mainly relates to an MP3 (MPEG1-layer3) compression domain audio segmentation method. Background technique [0002] Speaker retrieval technology refers to the technology of searching for a specific speaker from a large number of audio documents by using signal processing and pattern recognition methods. Audio segmentation is one of the key problems that speaker retrieval technology needs to solve. [0003] Most of the commonly used audio segmentation methods are carried out in the uncompressed domain, and the problems of directly segmenting audio in the compressed domain and detecting speaker change points are rarely involved. The data in the compressed domain comes from the encoded binary code stream of the original audio, and some characteristics of the original audio cannot be directly reflected from these data streams. Therefore, the audio segmentation in the compressed domai...

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): G10L17/00G10L19/00H03M7/30G06F17/30G10L15/04G10L21/02
Inventor 余小清万旺根常辽豫谭海英
Owner SHANGHAI UNIV
Features
  • Generate Ideas
  • Intellectual Property
  • Life Sciences
  • Materials
  • Tech Scout
Why Patsnap Eureka
  • Unparalleled Data Quality
  • Higher Quality Content
  • 60% Fewer Hallucinations
Social media
Patsnap Eureka Blog
Learn More

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

© 2025 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com