Unlock instant, AI-driven research and patent intelligence for your innovation.

Frequency-variable speech synthesis system and method based on sinusoidal model

A technology of speech synthesis and sinusoidal model, which is applied in speech analysis, speech recognition, instruments, etc. It can solve the problems that cannot be adjusted, the system cannot output according to the needs, and the application scene is fixed, so as to improve the accuracy, and the speech synthesis methods are diverse and rich. The effect of system application

Active Publication Date: 2019-12-10
SOUTH CHINA UNIV OF TECH
View PDF7 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

This voice system has the disadvantage of fixed application scenarios and cannot be adjusted according to different practical applications
When the voice that needs to be output is not recorded into the system, the system will not be able to output it as needed

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
  • Frequency-variable speech synthesis system and method based on sinusoidal model
  • Frequency-variable speech synthesis system and method based on sinusoidal model
  • Frequency-variable speech synthesis system and method based on sinusoidal model

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0050] The specific implementation of the present invention will be further described below with reference to the accompanying drawings. This embodiment takes a voice navigator as an example, but the implementation and protection of the present invention are not limited to this.

[0051] figure 1 It is a schematic diagram of the principle of variable frequency speech synthesis based on the sine model in the example. The invention extracts the sine component parameters of the speech through the sine model to establish a speech sine parameter library, and during speech synthesis, the speech information is extracted from the parameter library for synthesis according to the synthesis mode. The plan mainly includes two processes: the establishment of a speech sine parameter library and speech synthesis.

[0052] The establishment of the voice sine parameter library of the voice navigator of the present invention first performs framing processing on the voice signal, and then performs fa...

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 system and a method for synthesizing variable-frequency voice on the basis of sinusoidal models. The system comprises a power module, a voice input module, a synthesized voice output module, a control module, a processing module and a voice parameter storage module. The control module is connected with the voice input module, the processing module and the synthesized voice output module, the control module and the processing module are further connected with the voice parameter storage module, the power module is connected with the various other modules in the system, and integral devices can be powered by the power module. The system and the method have the advantages that sinusoidal component parameters of the voice are extracted, so that voice sinusoidal parameter databases can be established, the voice can be recorded in real time when voice information required to be outputted is not stored in the voice sinusoidal parameter databases of the system, the sinusoidal component parameters can be extracted, or the voice sinusoidal parameter databases can be enriched by means of network searching and downloading.

Description

Technical field [0001] The invention relates to the technical field of speech signal processing, in particular to a frequency conversion speech synthesis system and method based on a sine model. Background technique [0002] Using signal processing technology to analyze and synthesize speech signals is an important part of speech signal processing. The synthesis of speech can be used in fields such as voice navigators, hospitals and bank calling systems. Most of the voices used by existing voice navigators and voice calling systems are manually recorded and then simply processed, and then a segment of the voice is selected and played according to a specific application scenario. This kind of voice system has the disadvantage of fixed application scenarios and cannot be adjusted according to different practical applications. When the voice that needs to be output is not recorded into the system, the system will not be able to output as needed. [0003] The frequency conversion sp...

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): G10L15/08G10L15/18G10L15/183
CPCG10L15/08G10L15/18G10L15/183
Inventor 郑尚镇杨萃马碧云宁更新赵莹琦曹燕
Owner SOUTH CHINA UNIV OF TECH