Unlock instant, AI-driven research and patent intelligence for your innovation.

Deep neural network model, electronic device, identity validation method and storage medium

A deep neural network and identity verification technology, which is applied in the field of identity verification methods and storage media, deep neural network models, and electronic devices, can solve the problems of low accuracy and error-prone speaker recognition technology

Active Publication Date: 2018-09-21
PING AN TECH (SHENZHEN) CO LTD
View PDF6 Cites 23 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, in some limited cases, such as the collected effective speech of the speaker is short (speech duration less than 5 seconds), the accuracy of the existing text-independent speaker recognition technology is not high, and it is easy to make mistakes

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
  • Deep neural network model, electronic device, identity validation method and storage medium
  • Deep neural network model, electronic device, identity validation method and storage medium
  • Deep neural network model, electronic device, identity validation method and storage medium

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0055] The principles and features of the present invention are described below in conjunction with the accompanying drawings, and the examples given are only used to explain the present invention, and are not intended to limit the scope of the present invention.

[0056] The present invention proposes a deep neural network model for speaker identification and verification.

[0057] The structure of the deep neural network model of the present embodiment comprises:

[0058] The first layer structure: it is a neural network layer with the same preset structure that is stacked by multiple layers (for example, 9-12 layers), such as figure 1 As shown, the neural network layer of each preset structure includes: two CNN convolutional layers 100 connected in series (for example, the CNN convolutional layer 100 can adopt: a convolution kernel of 3*3 with a step size of 1*1 , the number of channels is 64), two modified linear units ReLU200, and a direct connection operation X that dir...

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 present invention discloses a deep neural network model, an electronic device, an identity validation method and a storage medium. The method comprises the steps of: obtaining standard voice datacorresponding to an identity to be validated after the current voice data of a target user to be subjected to identity validation, and performing framing processing of the two standard voice data to obtain a current voice frame set and a standard voice frame set; employing a preset filter to extract preset types of acoustic features of each voice frame in the two voice frame sets; inputting the extracted preset types of acoustic features to a pre-trained preset structure deep neural network model to obtain feature vectors with a preset length corresponding to the current voice data and the standard voice data; and calculating the cosine similarity of the two obtained feature vectors, and determining an identity validation result according to the calculated cosine similarity. The accuracy of speakers' identity validation is improved.

Description

technical field [0001] The invention relates to the technical field of voiceprint recognition, in particular to a deep neural network model, an electronic device, an identity verification method and a storage medium. Background technique [0002] Speaker recognition is usually called voiceprint recognition, which is a kind of biometric technology. It is often used to confirm whether a certain voice is spoken by a specified person. It is a "one-to-one discrimination" problem. Speaker recognition is widely used in many fields, for example, in finance, securities, social security, public security, military and other civilian security certification and other fields have a wide range of application requirements. [0003] Speaker recognition includes two methods: text-dependent recognition and text-independent recognition. In recent years, text-independent speaker recognition technology has continuously broken through, and its accuracy has been greatly improved compared with the p...

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): G10L17/00G10L17/02G10L17/04G10L25/24G10L25/30G06N3/04
CPCG10L17/02G10L17/04G10L25/24G10L25/30G10L17/00G06N3/045G06N3/084G06N3/048
Inventor 赵峰王健宗肖京
Owner PING AN TECH (SHENZHEN) CO LTD