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

Speaker recognition system and method based on MFCC and BP neural network

A BP neural network and speaker recognition technology, applied in the field of speaker recognition system, can solve the problem of not establishing the reliability index of recognition results, and achieve the effect of avoiding too long training time, quantifying reliability and improving recognition rate.

Active Publication Date: 2021-06-29
DONGFENG MOTOR GRP
View PDF11 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

The patent does not establish a reliability index for the recognition results

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
  • Speaker recognition system and method based on MFCC and BP neural network
  • Speaker recognition system and method based on MFCC and BP neural network
  • Speaker recognition system and method based on MFCC and BP neural network

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0020] Below in conjunction with accompanying drawing and specific embodiment the present invention is described in further detail:

[0021] Such as figure 1 The speaker recognition system based on MFCC and BP neural network is shown, which includes a speech signal preprocessing module 1, a speech signal windowing processing module 2, a spectrum analysis module 3, a filtering module 4, a discrete cosine transform module 5, and a BP neural network module 6 and the actual scene speaker recognition module 8, the speech signal preprocessing module 1 is used to carry out the signal preprocessing of framing, frame selection and pre-emphasis to the speech signal in turn, and the speech signal windowing processing module 2 is used for preprocessing After the voice signal is processed by windowing, the spectrum analysis module 3 is used to carry out spectrum analysis to the voice signal after the windowing process to obtain the frequency spectrum of each frame of the voice signal, and ...

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 speaker recognition system based on an MFCC (Mel Frequency Cepstrum Coefficient) and a BP (Back Propagation) neural network. A voice signal preprocessing module sequentially carries out framing, frame selection and pre-emphasis signal preprocessing on a voice signal, a voice signal windowing processing module carries out windowing processing on the preprocessed voice signal, a frequency spectrum analysis module performs frequency spectrum analysis on the voice signal after windowing processing, a filtering module performs Mel filtering processing on spectral line energy of each frame of frequency spectrum of the voice signal, and a discrete cosine transform module performs discrete cosine transform on each frame of frequency spectrum of the voice signal after Mel filtering. A BP neural network module generates a BP neural network training data set, establishes a corresponding BP neural network for each speaker, and trains each BP neural network. According to the invention, the reliability and accuracy of speaker recognition are improved.

Description

technical field [0001] The present invention relates to the technical field of speech recognition, in particular to a speaker recognition system and method based on MFCC and BP neural network. Background technique [0002] Speaker recognition, also known as voiceprint recognition, is different from speech recognition. Speech recognition is to determine the semantic information of speech, and speaker recognition is to use the speaker's voice features to identify or confirm the speaker's identity. [0003] According to different application purposes, speaker recognition can be divided into speaker identification and speaker confirmation. Speaker identification is used to determine which registered speaker the speech to be recognized is spoken by, and speaker verification is used to determine whether the speech to be recognized is spoken by the person the speaker claims. This patent belongs to the category of speaker recognition. [0004] According to the recognition method,...

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): G10L17/18G10L25/24G10L25/30
CPCG10L17/18G10L25/24G10L25/30
Inventor 高小清张浩刘浩罗挺刘年
Owner DONGFENG MOTOR GRP
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