Portable interpretation system based on WinCE platform and language recognition method thereof

A oral translation and portable technology, which is applied in the field of portable oral translation system, can solve the problems that embedded operating systems cannot be applied, and achieve the effect of low power consumption, low cost and high efficiency

Inactive Publication Date: 2011-11-09
GUANGDONG UNIVERSITY OF FOREIGN STUDIES +7
View PDF3 Cites 11 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Traditional speech recognition systems, such as Microsoft's SPEECHSDK 5.1 and Cambridge's HTK, are only speech recognition engines based on PC operating systems and cannot be applied to embedded operating systems.

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
  • Portable interpretation system based on WinCE platform and language recognition method thereof
  • Portable interpretation system based on WinCE platform and language recognition method thereof
  • Portable interpretation system based on WinCE platform and language recognition method thereof

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0032] The present invention is a portable oral translation system based on WinCE platform. It designs and implements a wince-based speech recognition system. The embedded system has low cost, low power consumption, high performance and other excellent qualities, and its core part is its embedded processing. At present, ARM microprocessors mainly include ARM7 series, ARM9 series, ARM9E series, ARM10E series, and ARM11 series, and their functions are becoming more and more powerful. The present invention uses embedded system scientific research platform UP-CPU 6410, adopts the latest S3C6410X (ARM11) embedded microprocessor of Samsung Company, its frequency reaches 633M, is a processor based on ARM1176JZF-S core, adopts ARMv6 framework.

[0033] The schematic diagram of the module of the present invention is as Figure 6 As shown, the voice signal collected by the voice collector 1 microphone is input, and the voice signal is pre-emphasized, framed, windowed, and endpoint detec...

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 relates to a portable interpretation system based on a WinCE platform, which comprises a voice collector, a voice preprocessing module, a voice feature extraction and modeling module, a model base, a recognition module, a corpus base and an interpretation and voice synthesis module, wherein all the modules are established on an embedded platform; the voice collection module is connected with the voice preprocessing module; the voice preprocessing module is connected with the voice feature extraction and modeling module; the voice feature extraction and modeling module is respectively connected with the model base or the recognition module; when a training state is selected, the voice feature extraction and modeling module is connected with the model base; when a recognition state is selected, the voice feature extraction and modeling module is connected with the recognition module; the recognition module is connected with the interpretation and voice synthesis module; and the interpretation and voice synthesis module is connected with the corpus base. The portable interpretation system has the characteristics of high voice recognition efficiency, high recognition accuracy, high equipment portability and two-way interpretation.

Description

technical field [0001] The invention relates to the technical field of voice recognition, in particular to a portable oral translation system based on the WinCE platform, which is used to recognize voice signals sent by people and convert them into corresponding translation results. The invention also relates to the speech recognition method of the translation system. Background technique [0002] Speech recognition technology is a technology that allows machines to convert voice signals from people into corresponding texts or make setting commands through recognition and understanding. It is gradually becoming the key technology of human-machine interface in information technology. In recent years, with the rapid development of embedded devices, consumer electronics products have penetrated into various fields of our lives, and their characteristics of portability and low cost have been widely used. Therefore, the embedded speech recognition system has great potential cons...

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): G10L15/02G10L15/06G10L15/14
Inventor 李心广阳爱民姚敏锋张晶马文华陈永煊林江豪
Owner GUANGDONG UNIVERSITY OF FOREIGN STUDIES
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