Embedded voice recognition system based on improved MFCC algorithm and method thereof
A technology of speech recognition and recognition method, applied in speech recognition, speech analysis, instruments, etc., can solve the problem of inability to recognize small languages or local languages, and achieve the effect of expanding the scope
Pending Publication Date: 2019-03-08
河北环铁技术开发有限公司
View PDF5 Cites 4 Cited by
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
[0004] For the problems referred to above, the purpose of the present invention is to provide a kind of embedded speech recognition system and method based on improved MFCC algorithm, it can realize the speech control of multiple equipment, and overcome the problem that can't identify small language or local language in the prior art
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 moreImage
Smart Image Click on the blue labels to locate them in the text.
Smart ImageViewing Examples
Examples
Experimental program
Comparison scheme
Effect test
Embodiment Construction
[0035] The present invention will be described in detail below in conjunction with the accompanying drawings and embodiments.
[0036] Such as figure 1 , figure 2 As shown, the present invention provides a kind of embedded speech recognition system based on improved MFCC algorithm, and it comprises fuselage 1, and the upper surface of fuselage 1 is provided with LCD display screen 2, menu key 3, power on / off key 4, return key 5 , confirmation key 6, left direction key 7, up direction key 8, right direction key 9, down direction key 10 and microphone groove 11. The LCD display screen 2 is located on the top of the upper surface of the fuselage 1, and the menu key 3, the power on / off key 4 and the return key 5 are located on the same horizontal line, and are arranged below the LCD display screen 2; the left arrow key 7, the upper arrow key 8, The right arrow key 9 and the down arrow key 10 are located in the middle of the upper surface of the fuselage 1, and are distributed i...
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
Login to View More Abstract
The invention relates to an embedded voice recognition system based on an improved MFCC algorithm and a method thereof. The method comprises the following steps: entering an identification mode, collecting a user voice signal and performing preprocessing; performing endpoint detection on the voice signal to determine a starting point and an ending point of the voice signal; and performing featureextraction on the voice signal to obtain a 12-dimensional mixed feature parameter, which can be all features of the voice signal input by the user; matching the obtained feature parameter with the feature templates pre-stored in a main control system, if matched, obtaining the final recognition result; otherwise, re-executing a recognition mode; wirelessly controlling the user-specified device bya Bluetooth module; performing selection to enter a training mode; selecting the storage points of the training templates by the user, if the storage point of each template already has a template, selecting one of the storage points for data coverage by the user; entering an training mode, obtaining the training template, and storing the training template in the feature template storage area of amain control system for feature matching of voice recognition.
Description
technical field [0001] The invention relates to an embedded speech recognition system and method, in particular to an embedded speech recognition system and method based on an improved MFCC algorithm. Background technique [0002] Through voice recognition, users do not need to press buttons or do other complicated operations, but only need to issue voice commands to control the operation of mechanical equipment. In addition, mobile terminal devices can quickly convert voice signals into text through voice recognition. Speech recognition technology has improved the efficiency of human production and life. At the same time, speech recognition is an important research direction of artificial intelligence and has broad development and progress. [0003] At present, many countries regard speech recognition as a key research project, and many companies have also launched speech recognition products. The existing speech recognition system has the following problems: 1. The speech...
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
Login to View More IPC IPC(8): G10L15/00G10L15/06G10L15/02G10L15/20G10L25/24
CPCG10L15/005G10L15/02G10L15/063G10L15/20G10L25/24
Inventor任彬赵增旭佟宽章胡佳辉
Owner河北环铁技术开发有限公司