Voice recognition method of computer and computer

A speech recognition and computer technology, applied in speech recognition, speech analysis, sound input/output, etc., can solve problems such as low speech recognition rate, failure to meet the requirements of home entertainment devices, and inconvenient use for users

Active Publication Date: 2013-04-03
SHANGHAI BEIJING UNIV FOUNDER TECH COMP SYST
View PDF0 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

For novice computer users or users with physical disabilities, it takes a long time to learn to use input devices such as mice and keyboards, which leads to inconvenience for users; at the same time, the trend of computers developing towards home entertainment devices has great impact on the convenience and ease of operation. Usability requirements are constantly improving, and the current input devices operated by hand cannot meet the requirements of home entertainment devices.
[0003] Although the existing voice recognition system can basically recognize all voices, the voice recognition rate is low, and multiple input of voice commands is required to improve the recognition rate

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
  • Voice recognition method of computer and computer
  • Voice recognition method of computer and computer
  • Voice recognition method of computer and computer

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0039] The invention provides a computer capable of recognizing voice commands, such as figure 1 As shown, it is realized by installing the speech recognition method on a computer. It includes a voice input device, a voice output device, an audio processing module, a buffer, a memory, a CPU, and a voice recognition system; the audio processing module includes an A / D converter, a D / A converter, a limiter, and a bandpass filter; The speech recognition system includes: a detection module, an analysis and recognition module, and an instruction execution module; the memory includes: an instruction font, an identification font, and a confirmation font;

[0040] The voice input device is an interface through which the user's voice information is input into the computer, and the voice input device can be a microphone, a microphone, etc.;

[0041] The limiter of the audio processing module filters out the noise below 40 decibels and above 60 decibels. It is located between the voice i...

example 2

[0053] figure 2 Show a flow chart of a speech recognition method, the steps of which are:

[0054] I Voice information is input from the voice input device;

[0055] The II voice input device transmits the voice information to the limiter and band-pass filter of the audio processing module for noise filtering and data format conversion;

[0056] III voice information is sent to the buffer by the audio processing module;

[0057] The detection module of the IV speech recognition system detects that there is voice information input in the audio processing module, and the detection module sends instructions to the analysis and recognition module of the speech recognition system;

[0058] The analysis and recognition module of the V speech recognition system transfers the speech information of the buffer and the instruction font information of the memory to search and compare respectively. If no matching information is found in the instruction font, the speech recognition syste...

example 3

[0062] image 3 Show another flow chart of speech recognition method, its steps are:

[0063] I Voice information is input from the voice input device;

[0064] The II voice input device transmits the voice information to the limiter and band-pass filter of the audio processing module for noise filtering and data format conversion;

[0065] III voice information is sent to the buffer by the audio processing module;

[0066] The detection module of the IV speech recognition system detects that there is voice information input in the audio processing module, and the detection module sends instructions to the analysis and recognition module of the speech recognition system;

[0067] The analysis recognition module of V speech recognition system transfers respectively the speech information of buffer and memory identification word library information and searches and compares; If no matching information is found in the identification word library, then the speech recognition sys...

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 voice recognition method of a computer and the computer. The voice recognition method is realized by being installed on the computer. The computer comprises a voice input device, a voice frequency processing module, a buffer, a storage, a CPU (Central Processing Unit) and a voice recognition system, wherein the voice frequency processing module comprises an A / D (Analog to Digital) converter, a D / A (Digital to Analog) converter, an amplitude limiter and a band-pass filter; the voice recognition system comprises a detection module, an analysis recognition module and an instruction execution module; and the storage is provided with an instruction word library. The voice recognition method comprises the following steps that: voice is input from the voice input device and transmitted to the voice frequency processing module for noise filtering and format conversion and then transmitted to the buffer; the detection module notifies the analysis recognition module when detecting that the voice exist, and the analysis recognition module respectively calls the voice information of the buffer and the instruction word library information of the storage for search and comparison; if the voice information is not found in the instruction word library, the voice recognition system is in a waiting state; if the voice information is found in the instruction word library, the instruction execution module opens a corresponding program through the matched voice information, and the CPU operates the program.

Description

technical field [0001] The invention relates to the field of computer application technology, in particular to a voice recognition method and a computer for executing recognition instructions. Background technique [0002] At present, the known way of using a computer is that the user transmits and executes instructions to the computer through input devices such as a mouse and a keyboard, and these devices must be executed by hand operations. For novice computer users or users with physical disabilities, it takes a long time to learn to use input devices such as mice and keyboards, which leads to inconvenience for users; at the same time, the trend of computers developing towards home entertainment devices has great impact on the convenience and ease of operation. Usability requirements are constantly increasing, and currently the input devices operated by hands cannot well meet the requirements of home entertainment devices. [0003] Although existing voice recognition sys...

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): G06F3/16G10L15/00G10L15/08
Inventor 高续赟甘金拓金香云
Owner SHANGHAI BEIJING UNIV FOUNDER TECH COMP SYST
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