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

Smoothly processing method for conversion of intervowel

A smoothing, vowel technology, applied in speech synthesis, speech analysis, instruments, etc., can solve problems such as insufficient processing and unnatural pronunciation.

Inactive Publication Date: 2006-07-05
INVENTEC BESTA CO LTD
View PDF0 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] The electronic dictionaries currently on the market are either not smoothed, or the processing is not good enough. Therefore, when two vowel phonemes are synthesized, the pronunciation will be unnatural.

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
  • Smoothly processing method for conversion of intervowel
  • Smoothly processing method for conversion of intervowel
  • Smoothly processing method for conversion of intervowel

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0026] Such as figure 1 As shown, the present invention is a smoothing processing method for inter-vowel transfer, which is used to merge two or more vowel phonemes, and make the merged inter-vowel phonemes have a smooth continuous effect during the transfer.

[0027] The voice data of each monophonic vowel phoneme used in the present invention is to take each sound frame (Frame; about 20 ~ 25ms) as a unit in advance, and coded into voice parameters such as spectrum parameters, pitch parameters and amplitude parameters, and store in memory. The present invention comprises the following steps:

[0028] Firstly, receive the vowel phoneme symbols and their merging sequence, which is step 101, that is, receive the phoneme symbols of two vowels pronounced continuously and their merging sequence.

[0029] And obtain the speech data, this is step 102, that is to obtain the two speech data respectively corresponding to the vowel phoneme symbols.

[0030] Concatenation of voice data...

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 smooth vowel warbling process includes connecting two vowel phonemes serially in the merging order while neglecting the mute between two phonetic data; converting phonetic frequency spectrum parameters in the connected phonetic data into LSF format; taking the last one third phonetic frame of the former vowel and the first one third phonetic frame of the latter vowel as the smooth warbling frame; re-calculating all the phonetic parameters inside the smooth warbling frame via linear interpolation process to obtain new phonetic data after smoothening treatment; merging the new phonetic data with the phonetic data before smoothening treatment and the phonetic data after smoothening treatment to form the warble tone data. The said process has smooth and continuous effect.

Description

technical field [0001] The invention relates to a smoothing processing method for transphonation between vowels, which can be applied to a speech synthesis method of an electronic dictionary, so that the processed two-vowel phoneme has a smooth continuous effect when transphoning. Background technique [0002] When electronic dictionaries synthesize voice data, because of the memory size, they often only store monophonic phonemes. Therefore, if the voice data of continuous vowels is not smoothed, unnatural pronunciation will occur. [0003] When pronouncing two phonemes, if you pronounce them one after the other, there will be an unnatural situation due to the pause between the two. Therefore, how to make the difference between the first phoneme and the second phoneme It is a very important technology to interleave the progressive sound transition smoothing process to produce the effect of continuity in pronunciation. [0004] The electronic dictionaries currently on the ma...

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): G10L13/00
Inventor 杨凰琳
Owner INVENTEC BESTA CO LTD
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