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

Voiceprint identifying method and device, server and storage medium

A voiceprint recognition and recognition technology, applied in the direction of instruments, voice analysis, etc., can solve the problems of poor recognition effect, achieve the effect of improving accuracy, improving recognition accuracy, reducing computational complexity and response time

Active Publication Date: 2018-09-21
京北方信息技术股份有限公司
View PDF8 Cites 5 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0005] Embodiments of the present invention provide a voiceprint recognition method and device, a server, and a storage medium to solve the problem in the prior art that the recognition effect is poor due to the loss of high-frequency part information of the voice

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
  • Voiceprint identifying method and device, server and storage medium
  • Voiceprint identifying method and device, server and storage medium
  • Voiceprint identifying method and device, server and storage medium

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0027] figure 1 It is a flow chart of the voiceprint recognition method provided by Embodiment 1 of the present invention. This embodiment is applicable to the situation of voiceprint recognition. The method can be executed by a voiceprint recognition device, which can use software and / or hardware way, and can be integrated on the server. Such as figure 1 As shown, the method specifically includes:

[0028] S110. Collect the voice signal to be recognized.

[0029] The voice signal to be recognized can be collected by a device with a sound collection function such as a microphone, and stored in any device with a storage function to wait for recognition, or the collected voice signal can be directly output to the voiceprint recognition device. device for further processing. During the collection process, the voice signal will be sampled and quantized accordingly. For example, the voice signal collected by a microphone is a signal that has been sampled and quantized.

[0030...

Embodiment 2

[0049] figure 2 It is a flow chart of the voiceprint recognition method provided by Embodiment 2 of the present invention, and this embodiment is further optimized on the basis of the foregoing embodiments. Such as figure 2 As shown, the method includes:

[0050] S210. Collect the voice signal to be recognized.

[0051] S220. Perform adaptive speech enhancement on the speech signal by using the improved self-disturbance least squares method.

[0052] After the speech signal to be recognized is collected, the improved Self-perturbing Recursive Least Squares (ISPRLS) method is used to enhance the speech signal adaptively, which can simultaneously achieve speech enhancement and effectively eliminate the background noise of the speech signal The purpose is to improve the signal-to-noise ratio of the speech signal and lay the foundation for the subsequent accurate extraction of voiceprint features.

[0053] S230. Perform fast Fourier transform on the speech signal after the s...

Embodiment 3

[0066] image 3 It is a flow chart of the voiceprint recognition method provided in Embodiment 3 of the present invention, and this embodiment is further optimized on the basis of the foregoing embodiments. Such as image 3 As shown, the method includes:

[0067] S310. Collect the speech signal to be recognized, and perform preprocessing including pre-emphasis, framing, windowing, endpoint detection and adaptive speech enhancement.

[0068] The collected speech signal is the original speech signal, pre-emphasize the original speech signal, enhance its high-frequency part to make the whole spectrum flat, and then divide the speech into frames to make short-term smooth processing, and then add Hamming window to avoid missing frames and The information between frames is then detected for endpoints to reduce the amount of data that needs to be processed, and finally background noise is eliminated through adaptive filtering while voice enhancement is achieved.

[0069] Wherein, ...

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

An embodiment of the invention discloses a voiceprint identifying method and device, a server and a storage medium; the method comprises the following steps: voice signals to be identified are collected; according to at least one improved Gammatone wave filter, the voice signals are subjected to frequency band-based voiceprint feature extraction operation, and voice signal identifying results areconfirmed based on extracted voiceprint features. The voiceprint identifying method and device, the server and the storage medium disclosed in the embodiment of the invention can be used for solving aproblem that poor identifying effects are caused due to information loss of a high frequency part of voice based on technologies of the prior art, a resolution ratio of the wave filter for the high frequency part of the voice can be improved, accuracy of the voiceprint feature extraction can be improved, identifying effects on the high frequency part of the voice can be improved, and computational complexity and response time involved in voiceprint identification can be reduced.

Description

technical field [0001] Embodiments of the present invention relate to the technical field of voice recognition, and in particular, to a voiceprint recognition method and device, a server, and a storage medium. Background technique [0002] As the user's awareness of safety precautions continues to increase, more and more identification methods consider using the user's physiological characteristics as an identification feature. Voiceprint recognition is an important and convenient identification method. Common representations of speech features involved in voiceprint recognition include Linear prediction cestrum coefficient (LPCC), Mel frequency cestrum coefficient (Mel frequency cestrum coefficient, MFCC) and cochlear frequency cestrum coefficient (Gammatone frequency cestrum coefficient). , GFCC). [0003] LPCC feature extraction is mainly based on the principle of linear prediction. It is believed that the speech sampling point can be predicted by the linear combination...

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): G10L17/02G10L25/24
CPCG10L17/02G10L25/24
Inventor 冉承祥高昊江杨飞
Owner 京北方信息技术股份有限公司
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