Imbedded voice synthesis method based on adaptive weighted spectrum interpolation coefficient

An adaptive weighting and speech synthesis technology, which is applied in speech synthesis, speech analysis, instruments, etc., can solve the problems of not being able to meet practical requirements, occupying a lot of computing resources, and having a large computing cost

Inactive Publication Date: 2011-10-12
北京宇音天下科技有限公司
View PDF3 Cites 1 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, the STRAIGHT synthesizer completes channel filtering through spectral convolution, which has a very large computational overhead and

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
  • Imbedded voice synthesis method based on adaptive weighted spectrum interpolation coefficient
  • Imbedded voice synthesis method based on adaptive weighted spectrum interpolation coefficient
  • Imbedded voice synthesis method based on adaptive weighted spectrum interpolation coefficient

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0024] as attached figure 1 As shown, in the embodiment of the present invention, the speech synthesis system is deployed in an embedded operating system, and the embedded speech synthesis system includes: a speech synthesis training terminal and a synthesis terminal. Wherein, the speech synthesis model training part is only used offline in the system, and is only used to generate the compressed model library required for the speech synthesis system to work; and the speech synthesis synthesis part (16) is completed on the chip. Since the present invention focuses on the extraction and synthesis of parameters, and the annotation text (17), text analysis (6), modeling, training and parameter generation are not the focus of the present invention, so the following focuses on parameter extraction and parameter reconstruction at the training end , and the synthesis filter selection on the synthesis side. In this embodiment, the LSP (line spectrum pair) parameter is selected as the ...

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 an imbedded voice synthesis method based on an adaptive weighted spectrum interpolation coefficient, which is used in an imbedded operation system for transforming arbitrary received characters into voices and outputting the voices. The method comprises the following steps of: at a training end, extracting a base frequency adaptive weighted spectrum interpolation (a STRAIGHT spectrum) for voice signals, extracting a track spectrum characteristic coefficient for the STRAIGHT spectrum, and modeling and training the characteristic coefficient through HTS; and at a synthesis end, after a characteristic coefficient sequence is calculated via a model, acquiring a synthesis voice by a traditional parameter synthesizer. When the method provided by the invention is used, the synthesis voice quality equivalent to that of a STRAIGHT synthesizer can be acquired, and the STRAIGHT synthesizer is replaced by the traditional parameter synthesizer at the synthesis end so as to greatly improve the synthesis speed, and the embedded application becomes possible.

Description

technical field [0001] The present invention generally relates to an embedded speech synthesis method based on adaptive weighted spectrum interpolation coefficients, especially for terminal equipment with limited storage and computing resources. Background technique [0002] With the vigorous development of mobile Internet and Internet of Things technology, embedded device terminals such as mobile phones and e-books have gradually become the most direct way for people to obtain and process information in daily life, while voice is the most natural and direct means of interaction. Therefore, embedded voice The development of synthesis technology is the trend of the times, and there is an urgent market application demand. [0003] The purpose of speech synthesis technology is to perfectly reproduce the human voice, that is, to enable the machine to imitate the characteristics of human voice, pronunciation style and rhythm. Traditional speech synthesis technology is based on l...

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): G10L13/02
Inventor 王朝民那兴宇谢湘何娅玲
Owner 北京宇音天下科技有限公司
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