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

A Singing Harmony Generation Method Based on Singing Rhythm

A singing voice and harmony technology, applied in the field of singing voice synthesis, can solve the problem that it is difficult for users to sing and match harmony, and achieve the effect of enriching music expressions, simple methods, and simplifying the beat extraction process.

Inactive Publication Date: 2021-03-02
FUZHOU UNIV
View PDF12 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Although the sound effect processing technology for K song applications is relatively mature, due to the limitations of their own voice and singing ability, it is difficult for users to match their singing voices

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 Singing Harmony Generation Method Based on Singing Rhythm
  • A Singing Harmony Generation Method Based on Singing Rhythm
  • A Singing Harmony Generation Method Based on Singing Rhythm

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0035] The technical solution of the present invention will be specifically described below in conjunction with the accompanying drawings.

[0036] The present invention proposes a singing harmony generation method based on singing rhythm, such as figure 1 It is mainly divided into three stages: in the rhythm detection stage, a flux filtering method is proposed for the singing voice and human auditory characteristics, and the end point intensity curve is obtained by using the spectral flux calculation, and then the BPM feature value is extracted; stage, a singing harmony generation algorithm is proposed for the singing harmony, the delay of the harmony part is dynamically calculated according to the BPM eigenvalue, and the pitch conversion algorithm with stable timbre is used to generate the same person harmony part; in the superposition synthesis stage, according to the delay and The dry-wet ratio uses a linear ratio to superimpose and output singing harmony. details as foll...

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 relates to a singing harmony generation method based on singing rhythm. Starting from the application of singing harmony, the singer's singing voice is detected based on the spectral flux, and the delay of the harmony part is adaptively adjusted according to the rhythm of the singing voice to generate harmony, which can simplify the beat extraction process and reduce time complexity. And enrich the soloist's musical expression. A singing harmony generation method based on singing rhythm proposed by the present invention is simple, flexible to implement, and has strong practicability.

Description

technical field [0001] The invention relates to the field of singing voice synthesis, in particular to a singing harmony generation method based on singing voice rhythm. Background technique [0002] As a relatively complex audio signal and artistic expression, singing voice is of great significance to its analysis and research. With the popularization of music entertainment, the sound effect processing of music speech has become a research and application hotspot, and has attracted extensive attention from academia and industry. Although the sound effect processing technology for karaoke applications is relatively mature, due to the limitations of their own voice and singing ability, it is difficult for users to match harmony for their own singing. Therefore, it has very important practical application value to study how to generate harmony based on singer's voice characteristics and how to generate adaptive harmony according to singing rhythm. Contents of the invention ...

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 Patents(China)
IPC IPC(8): G10L13/02G10H7/00
CPCG10H7/00G10H2250/455G10L13/02
Inventor 张栋彭建云汪培侨
Owner FUZHOU 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