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

Singing synthesis method and device

A synthesis method and technology of singing voices, applied in speech synthesis, voice analysis, instruments, etc., can solve problems such as differences in singing voices

Active Publication Date: 2019-01-04
GUANGZHOU KUGOU TECH
View PDF8 Cites 5 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0005] The embodiment of the present invention provides a singing voice synthesis method and device, which can solve the problem that the user's singing voice synthesized by the related technology is quite different from the user's voice

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
  • Singing synthesis method and device
  • Singing synthesis method and device
  • Singing synthesis method and device

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0041] In order to make the objectives, technical solutions, and advantages of the present invention clearer, the embodiments of the present invention will be described in further detail below in conjunction with the accompanying drawings.

[0042] figure 1 It is a flowchart of a singing voice synthesis method provided by an embodiment of the present invention. See figure 1 , The method includes:

[0043] 101. When the user's voice is acquired, extract the fundamental frequency, envelope, and consonant information of each word in the user's voice.

[0044] 102. According to the pitch frequency of each word in the song, adjust the fundamental frequency of each word in the user's voice. The pitch frequency of each word in the song is the frequency corresponding to the pitch of each word in the song. .

[0045] 103. Perform synthesis processing on the adjusted base frequency, the envelope of each word in the user's voice, and consonant information to obtain synthesized audio.

[0046] 10...

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 singing synthesis method and device, which belong to the technical field of speech synthesis. The method comprises the following steps: when a user speech is obtained, extracting the fundamental frequency, envelope and consonant information of each word in the user speech; adjusting the fundamental frequency of each word in the user speech according to the pitch frequencyof each word in a song, wherein the pitch frequency of each word in the song is the frequency corresponding to the pitch of each word in the song; synthesizing the adjusted fundamental frequency andthe envelope and consonant information of each word in the user speech to get a synthesized audio; and adjusting the length of each word in the synthesized audio according to the length of each word in the song to get synthesized user singing. The user singing is synthesized by using the original envelope and consonant information of the user, so that the original timbre of the user can be retained, and the synthesized user singing is closer to the voice of the user.

Description

Technical field [0001] The invention relates to the technical field of speech synthesis, in particular to a singing voice synthesis method and device. Background technique [0002] With the development of speech synthesis technology, speech synthesis technology has gradually been applied in people's daily life. For example, some users who sing with pentatonic incompleteness and hope to utter the lyrics and generate their own singing voice can be realized by using speech synthesis technology. [0003] At present, related technologies generally first recognize the user's speech, correspondingly find out the inherent singing voice in the speech synthesis database, and then extract the timbre of the singing voice, and then use the pre-established conversion model to turn the timbre of the singing voice into the user's timbre , Get the synthesized user singing voice. Among them, the filter model is used to convert the timbre of the inherent singing voice in the speech synthesis databas...

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): G10L13/02G10L13/033
CPCG10L13/02G10L13/033
Inventor 劳振锋
Owner GUANGZHOU KUGOU TECH
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