Semantics-based music retrieval method

A music and semantic technology, applied in the field of music retrieval system, to achieve the effect of easy modification and subjective experience

Inactive Publication Date: 2018-07-27
DALIAN UNIV
View PDF4 Cites 20 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

In addition, similar music databases are mostly concentrated in Western music, and there are few music databases that complete automatic semantic annotation for Chinese songs

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
  • Semantics-based music retrieval method
  • Semantics-based music retrieval method
  • Semantics-based music retrieval method

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0014] The invention provides a music retrieval method based on a semantic data set. The function of this method is that it can map audio content to a label-based semantic feature space by using a semantic annotation model, trying to overcome the difficulty of extracting acoustic features. Find the connection between raw signal and semantics. At the same time, the crawled music in the music database is also automatically marked using the trained model, so that the similarity between the retrieval example and the music database is compared in the semantic space, and semantically related music is obtained. A well-designed user interface , to fully express the semantic information to the user, and at the same time facilitate the user to make corresponding modifications to the semantic expression, and facilitate the user to express personal subjective feelings about a certain music. Saving user annotation information on songs is conducive to expanding Chinese music datasets, there...

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 semantics-based music retrieval method, belongs to the field of cloud computing big data, and solves the problem of lack of effective automatic semantic tagging and interactive retrieval in a Chinese song data set. According to the technical key points, starting from original audio bottom features, audio contents are mapped to a tag-based semantic feature space by utilizing a semantic tagging model. The effects are that a system can obtain a user retrieval intention more naturally and accurately, so that a user can obtain better retrieval experience and conveniently find and discover wanted songs.

Description

technical field [0001] The invention relates to a retrieval system, in particular to a music retrieval system based on semantic data. Background technique [0002] The semantics experienced in music, such as user subjective feelings such as mood and style, are one of the important factors that encourage people to listen to and pursue music. As a high-level semantic feature of music, music semantic recognition and semantic-based retrieval have always been the difficulties and hotspots of researchers in the field of Music Information Retrieval (MIR). The "gap" between the underlying physical features of music and the high-level semantic features has plagued and restricted the development of content-based music retrieval research. With the development of technology and the deepening of research, researchers have established the connection between musical features and semantics in various ways, gradually narrowing the gap. Many research works, such as emotion classification ba...

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): G06F17/30G10L15/06G10L15/08
CPCG10L15/063G10L15/08G06F16/683G06F16/686
Inventor 季长清秦静汪祖民闫妍
Owner DALIAN 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