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

A method for analyzing the matching degree of lyrics and songs

A song matching and analysis method technology, applied in the field of data processing, can solve problems such as low matching accuracy, unsatisfactory singers, mismatching lyrics and songs, etc., and achieve the effect of reducing the difficulty of understanding, facilitating the difficulty of understanding, and reasonable design

Active Publication Date: 2019-03-29
TIANJIN UNIV +1
View PDF4 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0003] As for the existing lyrics matching classification method, firstly, it cannot evaluate the matching between the lyrics written in any tonal dialect and the song score, and can only support the pronunciation of Mandarin Chinese, which cannot meet the needs of singers; secondly, the matching is accurate The accuracy is low, which often leads to the phenomenon that the lyrics do not match the song, which affects the user experience

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
  • A method for analyzing the matching degree of lyrics and songs
  • A method for analyzing the matching degree of lyrics and songs
  • A method for analyzing the matching degree of lyrics and songs

Examples

Experimental program
Comparison scheme
Effect test

Embodiment

[0031] When using the lyrics and song matching analysis method to evaluate the score of one sentence in "The Hill", "over the hill, although I have turned white, I chatter endlessly", first train the classifier, and collect training data according to the language with tones. For the four tones of Mandarin Chinese, the data of four types of utterances (one, two, three, and four tones) are collected, and at least 1,000 utterances of each type are used as the training set data. The time-spectrum transformation of the collected sound is performed to obtain a two-dimensional image, and the two-dimensional image and the corresponding tone are input into the classification algorithm.

[0032] Then, collect the lyrics and music of the song, convert the song into a function of frequency changing with time, and intercept according to the lyrics to obtain a series of two-dimensional time-spectrum images of the music score itself.

[0033] Finally, the two-dimensional time-spectrum image ...

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 method for analyzing the matching degree of lyrics and songs, which comprises the following steps of: generating two-dimensional images by using a time-frequency spectrum algorithm for pronunciation of a large number of Chinese characters; using the corresponding pronunciation training classifier, wherein the classifier can give the corresponding four probability scores of the four tones of the two-dimensional image generated by the sound converted by the spectrum algorithm in any use time. 2-D image of that song itself are generated by the time-frequency spectrum algorithm of the music spectrum; The evaluator inputs the two-dimensional image of the song itself to the classifier, and the classifier gives the most suitable tone to the most unsuitable tone in order,and returns to the evaluator; The lyrics are imported into the evaluator through the input tone, and the evaluator gives the matching score according to the information provided by the lyrics. The method can grade one word, one sentence or the whole lyrics, thereby helping musicians to improve the lyrics or music, thereby avoiding the phenomenon of not understanding the song without reading the lyrics, and making the song more popular.

Description

technical field [0001] The invention relates to an analysis method, in particular to a method for analyzing the matching degree of lyrics and songs, and belongs to the technical field of data processing. Background technique [0002] At present, many mobile devices support the music playback function. The music playback tool is a multimedia playback software used to play various music files. At present, the audio playback tool can search for lyrics according to the matching classification method of lyrics, and the server will search for a version The lyrics of the song are recommended to the audio playback tool, and then the recommended version of the lyrics will be displayed during playback. At the same time, when singing, it can also be matched with the song according to the singer's pronunciation, so that the singer can understand the audience's possible understanding difficulties. Targeted application of singing skills in the corresponding part of the song to reduce the ...

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): G06F16/63G06F16/638G06F16/68G06K9/62
CPCG06F18/2411
Inventor 李永徽刘彦迪牛徐策李胡林代玉
Owner TIANJIN UNIV
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Patsnap Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Patsnap Eureka Blog
Learn More
PatSnap group products

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

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com