Human voice synthesis method, device and equipment for Buddhist music and storage medium

A synthesis method and human voice technology, applied in speech synthesis, speech analysis, instruments, etc., can solve the problems of low efficiency of human voice synthesis, achieve the effect of improving the efficiency of human voice synthesis, reducing costs, and improving the auditory experience

Pending Publication Date: 2021-06-29
PING AN TECH (SHENZHEN) CO LTD
View PDF0 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] The main purpose of the present invention is to solve the technical problem that the human voice synthesis efficiency of existing vocal synthesis model is low

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
  • Human voice synthesis method, device and equipment for Buddhist music and storage medium
  • Human voice synthesis method, device and equipment for Buddhist music and storage medium
  • Human voice synthesis method, device and equipment for Buddhist music and storage medium

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0064] In view of the above problems, this application realizes the conversion from musical score to human voice by proposing to convert the musical score information into a single feature sequence, and synthesize the converted data into Buddhist music audio corresponding to the musical score information through a vocoder synthesizer. This method is conducive to taking the information in the score into consideration. At the same time, in the phoneme part, we take the rhyme angle of Chinese into account, which is more in line with Chinese pronunciation. At the same time, this method is used to synthesize human voice. The pitch and breath of the generated Buddhist music audio are relatively stable, which improves the user's listening experience and improves the efficiency of human voice synthesis.

[0065] The terms "first", "second", "third", "fourth", etc. (if any) in the description and claims of the present invention and the above drawings are used to distinguish similar obje...

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 the technical field of artificial intelligence, and discloses a human voice synthesis method, device and equipment for Buddhist music and a storage medium. According to the method, music theory data, lyrics and position information of each character in the lyrics in the music theory data are extracted from music score information by utilizing a music track capturing algorithm, a preset Buddha knowledge dictionary is queried based on the lyrics, the lyrics are converted into a pinyin sequence, syllables of pinyin of each character in the pinyin sequence are recognized, the voice pronunciation of each syllable is determined according to the music theory data to obtain an acoustic feature sequence corresponding to the lyrics, the acoustic feature sequence is synthesized into a Buddha music audio corresponding to the music score information through a sound code synthesizer, the music score information of Buddha music is converted into human voice based on the syllables of Pinyin, and synthesis is carried out. The generated Buddhist music audio is stable in pitch and breath, the auditory experience of a user is improved, and the human voice synthesis efficiency is improved.

Description

technical field [0001] The present application relates to the technical field of artificial intelligence, and specifically relates to a human voice synthesis method, device, equipment and storage medium for Buddhist music. Background technique [0002] As a high-level product of human intelligence activities, music has a rather complex structure. With the maturity of speech synthesis technology, it has been widely used in transportation, education, medical and social fields. Such as traffic voice navigation, language learning pronunciation, medical voice control, etc., which facilitate people's work and life. And further singing voice synthesis technology, taking into account the influence of music scores, the pronunciation of each note is rich and varied, greatly increasing the technical difficulty of singing voice synthesis. [0003] At present, the synthesis of songs is mainly done by recording some voices, and then editing the recorded voices through software for simpl...

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): G10L13/04
Inventor 蒋慧军
Owner PING AN TECH (SHENZHEN) 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