System for building music classification model, system for recommending music and corresponding method

A classification model and music technology, applied in the computer field, can solve problems such as the unscientific music recommendation effect of the music classification model, and achieve the best experience effect

Active Publication Date: 2013-07-03
BEIJING BAIDU NETCOM SCI & TECH CO LTD
View PDF12 Cites 42 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] The present invention provides a system and method for establishing a music classification model and a system and method for rec

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
  • System for building music classification model, system for recommending music and corresponding method
  • System for building music classification model, system for recommending music and corresponding method
  • System for building music classification model, system for recommending music and corresponding method

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0034] Embodiment 1. This embodiment provides a system for establishing a music classification model, see figure 1 As shown, it includes: a first feature extraction unit 101 , a first feature splicing unit 102 , and a model training unit 103 .

[0035] Wherein, the first feature extraction unit 101 is configured to extract acoustic feature vectors of different dimensions for each piece of music in the training data.

[0036] In the training phase, the corresponding music will be selected in advance according to different music styles as the training data. In the training process, the acoustic features of different dimensions extracted by the present invention for training data may include but not limited to acoustic feature vectors of different dimensions formed by any combination of the speed, strength, timbre, and melody of the song. In the embodiment of the present invention In the description of , the simultaneous use of these four acoustic features is taken as an example...

Embodiment 2

[0040] Embodiment 2. This embodiment provides a system for establishing a music classification model, see figure 2 As shown, it includes: a first feature extraction unit 201 , a first feature splicing unit 202 , a first feature dimensionality reduction unit 203 , a model training unit 204 , a model library unit 205 , a user feedback unit 206 and an adaptive adjustment unit 207 .

[0041] Wherein, the description about the first feature extraction unit 201 and the first feature splicing unit 202 is consistent with the first embodiment, and will not be repeated here.

[0042] The first feature dimensionality reduction unit 203 is configured to provide the supervectors of each music to the model training unit 204 after removing the correlation information of each dimensional acoustic feature vector in the supervector obtained by the first feature splicing unit 202 . Specifically, due to the high dimensionality of the supervector (such as: four dimensions), and there will be corr...

Embodiment 3

[0054] Embodiment 3. This embodiment provides a method for establishing a music classification model, see image 3 shown, including the following steps:

[0055] S301. Extracting acoustic feature vectors of different dimensions for each piece of music in the training data.

[0056] In the training phase, the corresponding music will be selected in advance according to different music styles as the training data. Specifically, in the training process, the acoustic features of different dimensions extracted by the present invention for the training data may include but not limited to acoustic feature vectors of different dimensions formed by any combination of the speed, strength, timbre, and melody of the song. In the description of the embodiments of the invention, the simultaneous use of these four acoustic features is taken as an example for description. These four acoustic features describe the style of a song from different perspectives, and songs with similar styles mus...

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 provides a system for building a music classification model, a system for recommending music and a corresponding method, which are used for solving the problems of non scientific music classification module and poor music recommending effect in the prior art. The system for building the music classification model comprises a first characteristic extraction unit, a first characteristic split joint unit and a model training unit. The system for recommending music comprises a second characteristic extraction unit, a second characteristic split joint unit, a matching unit and a recommending unit. The method for building the music classification module comprises the following steps that different dimensions of acoustic characteristic vectors are extracted by aiming at each piece of music in training data; different dimensions of acoustic characteristic vectors are split into super vectors according to the preset sequence by aiming at each piece of music; and the super vectors of each piece of music in different music styles are utilized for training a GMM (Gaussian mixture model). The GMM utilized by the method for recommending music is obtained by the method for building the music classification model.

Description

technical field [0001] The invention relates to the field of computer technology, in particular to a system and method for establishing a music classification model, and a system and method for recommending music. Background technique [0002] The description method of music style in the prior art usually utilizes text label features. Music style classification based on text tags, relying on users' listening behavior and preferences to mark different music with feature tags of different dimensions, using text processing technology for music classification and personalized recommendation. [0003] The biggest defect of the existing music recommendation technology based on the above-mentioned text tags is that it is unfavorable for some unpopular songs. The more difficult it is to recommend" cycle, resulting in "unpopular effect", which is unfair to unpopular songs. Contents of the invention [0004] The present invention provides a system and method for establishing a mus...

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): G06F17/30G10H1/00
Inventor 宋辉
Owner BEIJING BAIDU NETCOM SCI & TECH CO LTD
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