Music continuous emotion feature analysis evaluation method based on Gamma distribution analysis

A technology of emotional features and music features, which is applied in the field of music continuous emotional feature analysis and evaluation, can solve problems such as inaccurate music selection or recommendation, and inability to make real-time music recommendations, so as to reduce the number of features, reduce overfitting, and improve model accuracy degree of effect

Active Publication Date: 2018-01-12
HARBIN INST OF TECH +1
View PDF5 Cites 3 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

On the one hand, this approach will cause inaccurate music selection or recommendation, and on the other hand, it will not be able to perform real-time music recommendation

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
  • Music continuous emotion feature analysis evaluation method based on Gamma distribution analysis
  • Music continuous emotion feature analysis evaluation method based on Gamma distribution analysis
  • Music continuous emotion feature analysis evaluation method based on Gamma distribution analysis

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0061] A kind of music continuous emotion feature analysis and evaluation method based on Gamma distribution analysis The specific steps are as follows:

[0062] Step 1: Calculate the correlation between music features and emotional labels; set the music signal as A i , 1≤i≤N, N is the number of samples, the emotional label of Valence and Arousal in the process of the user listening to music is L, and the sampling rate is 2Hz,

[0063] (4) In order to preserve the time information, the music signal is firstly windowed and divided into frames. The length of the music emotion analysis takes the window length w as 4 seconds, and the frame shift as 0.5 seconds.

[0064] (5) Secondly, audio feature extraction, feature F ij , 1≤j≤M, M is the feature dimension, including low-level features, pitch and loudness, and high-level semantic features, melody and rhythm;

[0065] (6) Calculate each dimension feature F ij , 1≤j≤M and the Pearson correlation coefficient of scoring L, the Pea...

Embodiment 2

[0104] In order to verify the recognition effect of the optimal feature set extracted by the music continuous emotion feature evaluation method based on Gamma distribution analysis, we tested the method on the MediaEval 2013 public music emotion dataset and compared it with other methods. The dataset contains 744 music clips with a length of 45 seconds and continuous emotion annotations for these music clips. The method that the present invention proposes is to the average fitting coefficient of different feature numbers, the calculated result is as follows table 1.

[0105] Table 1 Fitting coefficient table under different K values ​​(number of features)

[0106] Trials

K value

rSquare

1

2

0.17

2

100

0.28

3

200

0.35

4

600

0.38

[0107] In order to obtain the best fitting coefficient, we calculate the fitting coefficient every 50, the result is as follows image 3 shown. When taking the first 600-dimensio...

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 music continuous emotion feature analysis evaluation method based on Gamma distribution analysis. The method includes the steps: firstly, building a Gamma distribution analysis evaluation method of music continuous emotion features, and finding emotion features most similar to emotion responses on a time sequence by the method; secondly, building an emotion feature analysis method based on an emotion perception matrix, evaluating the features from emotion perception ability by the method, and finding emotion features with best perception ability; finally, automaticallyanalyzing music emotions in real time based on Gamma distribution emotion analysis forecasting method. According to the method, the music emotions can be automatically analyzed, emotion tags are automatically forecasted, bases are provided for evaluation and selection of the music emotions, and the method has promoting effects on aspects such as artificial intelligence and emotion perception.

Description

technical field [0001] The invention relates to a music continuous emotion feature analysis and evaluation method based on Gamma distribution analysis. Background technique [0002] The research on music emotion automatic recognition has a history of more than ten years, but so far, the research work is still in a relatively early stage, and the accuracy rate of music emotion recognition is still relatively low. The main reasons are as follows: (1) the lack of effective features of music emotion; (2) the emotion expressed by music is subjective and difficult to quantify. In essence, music is the arrangement and combination of sounds of different loudness, frequency and timbre. Music expresses its emotions with the difference of melody, the speed of rhythm, the strength of voice, the change of harmony, and the difference of timbre. Therefore, how to extract the acoustic features related to emotion plays a crucial role in the automatic analysis of music emotion. In addition...

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): G10L25/63
Inventor 李海峰马琳薄洪健丰上李洪伟刘全胜信家男
Owner HARBIN INST OF TECH
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