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

Automatic sound identifying treating method for embedded sound identifying system

An automatic speech recognition and speech recognition technology, applied in speech recognition, speech analysis, sound input/output, etc., can solve the problems of not considering the distinguishing performance of speech command templates, the rejection of non-command words is too simple, and the performance needs to be further improved. , to achieve the effect of strong representation, high recognition rate and low cost

Inactive Publication Date: 2005-03-02
SHANGHAI JIAO TONG UNIV
View PDF1 Cites 23 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

It directly applies training voice compression to form templates, without considering the difference between voice command templates, which affects the recognition effect
It uses a probability-based identification method, which is complex to calculate and is not suitable for applications in embedded systems with high real-time performance requirements.
At the same time, the endpoint detection method it uses needs to improve its adaptability to the environment, and the rejection of non-command words is too simple, and its performance needs to be further improved

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
  • Automatic sound identifying treating method for embedded sound identifying system
  • Automatic sound identifying treating method for embedded sound identifying system
  • Automatic sound identifying treating method for embedded sound identifying system

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0019] Embodiments of the present invention are described in detail in conjunction with each figure as follows:

[0020] The structure of the embedded speech recognition core is as follows: Figure 4 As shown, it includes DSP unit for calculation and control; FlashROM for storing programs and voice recognition templates; A / D converter and microphone for voice input, and programmable logic device CPLD for decoding and output control . Description: MIC: microphone, A / D: analog-to-digital converter, DSP: digital signal processor, RAM: random access memory, FlashROM: flash memory, CPLD: programmable logic device.

[0021] The voice processing process of the present invention can be divided into four parts: front-end processing, real-time recognition, back-end processing and template training. figure 1 described as follows:

[0022] 1. Front-end processing:

[0023] (1) Sampling the speech signal through an A / D (analog-to-digital) converter, and pre-emphasizing and windowing an...

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 is a voice automatic-identification processing method of embedded voice identifying system, composed of a front-end processing part, a real-time identifying part, a back-end process part and a template training part, adopting self-adapting end-point detecting technique to draw voiced segments, adopting synchronous mode to identify input voice, applying vector-supporting algorithm to realize fast rejection of non-command voice, thus improving identification reliability and practicality, and adopting multistage vector quantization method to train the voice template and assorted with McE / GPD distinctive training to optimize the voice template so as to improve identifying property. The used acoustic model has a small memory space, thus effectively increasing the identification ratio of the system to above 95%, its algorithm load is small, its memory space is small and its identification rejection ratio is higher than 80%.

Description

technical field [0001] The invention relates to an automatic speech recognition processing method, in particular to an automatic speech recognition processing method of an embedded speech recognition system. It is used in the field of intelligent information processing technology. Background technique [0002] The application of speech recognition technology can be divided into two development directions: one direction is the large vocabulary continuous speech recognition system, which is mainly used in computer dictation machines, and voice information query service systems combined with telephone networks or the Internet. It is implemented on a computer platform; another important development direction is the embedded voice recognition system, which is the application of miniaturized and portable voice products, such as dialing on wireless mobile phones, voice control of automotive equipment, smart toys, remote control of home appliances, The application of voice interact...

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): G06F3/16G10L15/02G10L15/06G10L15/28
Inventor 朱杰蔡铁
Owner SHANGHAI JIAO TONG UNIV
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