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

Modeling method for enhancing expressive force of text-to-speech (TTS) system

A modeling method and technology of speech synthesis, applied in speech synthesis, speech analysis, speech recognition, etc., can solve problems such as affecting the accuracy of the fundamental frequency model

Inactive Publication Date: 2011-07-13
王程程
View PDF0 Cites 3 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Such modeling together will inevitably affect the accuracy of the fundamental frequency model with a smaller dimension

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
  • Modeling method for enhancing expressive force of text-to-speech (TTS) system
  • Modeling method for enhancing expressive force of text-to-speech (TTS) system
  • Modeling method for enhancing expressive force of text-to-speech (TTS) system

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0043] (1) Model training: In the case of ensuring that the phoneme boundaries of the fundamental frequency and spectrum are the same as the original baseline system, observe the performance of the fundamental frequency model and fundamental frequency parameter prediction through respective asynchronous modeling. In fact, this is a semi-asynchronous approach. The reason why it is not fully asynchronous is that we consider the following issues: If the fundamental frequency and spectrum are modeled without the same phoneme boundary, the phoneme boundary of the fundamental frequency will be due to Some sounds that start and end with unvoiced sounds are not divided correctly; when synthesizing, we also have a big alignment problem because the fundamental frequency and spectrum are completely asynchronous. Specific steps are as follows:

[0044] I. The training starts, and the initial steps are the same as the original synchronous modeling system until the initial clustering hidden...

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 modeling method for enhancing the expressive force of a text-to-speech (TTS) system. The modeling method is characterized in that the concept of asynchronous modeling of two acoustic features namely fundamental frequency and frequency spectrum is introduced into the Trainable TTS. The method comprises the following steps: performing independent model training under the condition of the same phoneme boundary of the fundamental frequency and the frequency spectrum; and finally generating parameters respectively according to a parameter generating algorithm, and then performing TTS, thus enhancing the expressive force in synthetic speech quality.

Description

technical field [0001] The invention relates to the field of speech synthesis, and specifically proposes a method for asynchronously modeling two acoustic features of fundamental frequency and frequency spectrum in speech synthesis, so as to improve the sound quality of synthesized speech and make its rhythm more abundant. Background technique [0002] The research on speech synthesis technology has a history of more than 200 years, but modern speech synthesis technology with real practical significance is developed with the development of computer technology and digital signal processing technology, mainly to enable computers to generate high-definition , High natural continuous speech. In the development of speech synthesis technology, the early research mainly used the parametric synthesis method, and later with the development of computer technology, the synthesis method of waveform splicing appeared. [0003] In the development of speech synthesis technology, the early...

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): G10L13/02G10L13/04G10L15/02G10L15/06G10L15/14
Inventor 王程程
Owner 王程程
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