Chinese voice synthesis method based on music instrument digital interface algorithm

A technology of speech synthesis and Chinese, applied in speech synthesis, speech analysis, instruments, etc., can solve problems such as unnatural transition of speech units, high system performance requirements, and huge storage requirements, and achieve portability guarantee and scalability Guaranteed effect

Inactive Publication Date: 2004-04-07
FUDAN UNIV
View PDF0 Cites 1 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, there is still a certain gap between the speech synthesized based on the splicing method and the natural speech. The main performance is that the naturalness of the synthesized speech is not high enough, and the transition between speech units is not natural enough.
However, there are some inherent defects in the above speech synthesis method: either the synthesis algorithm is relatively complicated, and the performance requirements of the system are relatively high; or the storage requirements are quite large
Poor portability and scalability

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
  • Chinese voice synthesis method based on music instrument digital interface algorithm
  • Chinese voice synthesis method based on music instrument digital interface algorithm
  • Chinese voice synthesis method based on music instrument digital interface algorithm

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0051] For example, PC-based speech synthesizer is used: in the operating system of Win95 and above, it is only necessary to add the corresponding speech waveform library in its wave table file (gm.dls), and the others do not need any modification. Any software that plays MIDI files in the system can synthesize voice signals normally.

[0052] We store a waveform of "āo" and a "ī" in the form of a stringed instrument in the DLS wave table, and the correction parameters of their three tones are: 1. Yangping, no down section and decay section, hold time 0.3 milliseconds, Release time 0.3 milliseconds. The frequency is raised by 600 cents. 2. For the upper sound, there is no sound in the lower part, the decay time is 0.3 milliseconds, the hold time is 0.3 milliseconds, and there is no sound in the release part. The frequency drops by 600 cents. 3. To remove the sound, the press time is 0.1 milliseconds, the decay time is 0.4 milliseconds, the hold section is not, and the relea...

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 present invention is one kind of Chinese voice synthesis method based on MIDI algorithm. The method includes establishing waveform library via storing Chinese voice including 23 initial consonants and 34 vowels in DLS wavetable, attaching the waveform library to the tail of the standard DLS wavetable, performing ADSR correction to vowels, converting text first into spelling and then into MIDI message, and final synthesizing Chinese character voice via sound card or other MIDI backing-up player. The present invention can compress greatly the memory space, reduce operation amount and save system cost, and has excellent porting performance and expandability.

Description

technical field [0001] The invention belongs to the technical field of Chinese speech synthesis, and specifically relates to a Chinese speech synthesis method based on a musical instrument digital interface algorithm. technical background [0002] Speech synthesis technology is to convert the text information generated by the computer or input from the outside into a speech signal output according to the speech processing rules, so that the computer can read the text information. Speech synthesis technology involves many fields such as acoustics, linguistics, digital signal processing technology, multimedia technology, etc. It is one of the hot technologies that the world's powerful countries are competing to research. At present, speech synthesis technology mainly includes rule-based synthesis and splicing-based synthesis. Rule-based synthesis is mainly to calculate the trajectory formation rules of parameters to complete the parameter synthesis of speech; splicing-based s...

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): G10L13/00
Inventor 陈光梦李涛胡波
Owner FUDAN UNIV
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