Summarizing digital audio data

A technology of voice data and abstract, applied in the field of data analysis, can solve the problem that the quality of the abstract cannot meet the needs and so on

Inactive Publication Date: 2006-01-11
AGENCY FOR SCI TECH & RES
View PDF1 Cites 6 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Especially when it is necessary to make summaries of various types of music, the quality of the summaries produced by this method cannot meet the needs

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
  • Summarizing digital audio data
  • Summarizing digital audio data
  • Summarizing digital audio data

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0023] figure 1 It is a block diagram of components and / or modules of the system 100 for generating a sound abstract according to an embodiment of the present invention. The system receives a sound file such as music content 12 at a segmenter 114 . The music sequence 12 is segmented into frames and features are extracted from each frame at a feature extractor 116 . The classifier 118 classifies the frames whose features are extracted, such as the pure music sequence 140 or the vocal music sequence 160 , according to the classification parameters provided by the classification parameter generator 120 . When there is no singing voice in the music content, it is defined as pure music, and when there is singing voice, it is defined as vocal music. The sound summary is generated in the music summary device 122 or 124, and the music summary device makes a summary for the sound content specially set up for this category or makes a summary for the sound content classified by the cla...

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

An embodiment is related to automatic summarization for digital audio raw data (12), more specifically, for identifying pure music and vocal music (40,60) from digital audio data by extracting distinctive features from music frames (73,74,75,76), designing a classifier and determining the classification parameters (20) using adaptive learning / training algorithm (36), and identifying music into pure music or vocal music according to the classifier. For pure music, temporal, spectral and cepstral features are calculated to characterise the musical content, and an adaptive clustering method is used to structure the musical content according to calculated features. The summary (22,24,26,48,52,70,72) is created according to clustered result and domain-based music knowledge (50,150). For vocal music, voice related features are extracted and used to structure the musical content, and similarly, the music summary is created in terms of structured content and heuristic rules related to music genres.

Description

technical field [0001] The present invention relates to data analysis, such as sound data indexing and classification. More specifically, the present invention relates to automatic summarization of digital music raw data for a variety of applications such as content-based music retrieval and web-based online music distribution. Background technique [0002] The rapid development of computer network and multimedia technology has made the scale of digital multimedia datasets grow rapidly. To accommodate development, there is a need to produce concise and informative summaries for large multimedia datasets, which should best capture important elements of the original content in large-scale information organization and processing. So far, many techniques for automatically creating summaries of text, audio and video have been proposed and are constantly being developed. However, making a music summary refers to determining the most popular and prominent main theme part of a pie...

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): G06F17/00G06F17/30G10H1/00G10L11/00
CPCG10H2240/155G10L25/48G10H1/0008G06F17/30743G10H2210/031G10H2210/046G06F17/30775G10H2210/061G06F16/64G06F16/683
Inventor 徐常胜
Owner AGENCY FOR SCI TECH & RES
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