Method for training speaker recognition network model, speaker recognition method and system

A technology of speaker recognition and network model, applied in the field of speaker recognition network model training, speaker recognition method and system, can solve the problem of low speaker recognition accuracy, and achieve the effect of high recognition ability and low error rate

Active Publication Date: 2018-08-17
AISPEECH CO LTD
View PDF22 Cites 35 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] Embodiments of the present invention provide a speaker recognition network model training method, speaker recognition method and system, which can at least be used to solve the technical problem of low speaker recognition accuracy 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 more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • Method for training speaker recognition network model, speaker recognition method and system
  • Method for training speaker recognition network model, speaker recognition method and system
  • Method for training speaker recognition network model, speaker recognition method and system

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0055] In order to make the purpose, technical solutions and advantages of the embodiments of the present invention clearer, the technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments It is a part of embodiments of the present invention, but not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by persons of ordinary skill in the art without creative efforts fall within the protection scope of the present invention.

[0056] It should be noted that, in the case of no conflict, the embodiments in the present application and the features in the embodiments can be combined with each other.

[0057] The invention may be described in the general context of computer-executable instructions, such as program modules, being executed by a computer. Generally, program mo...

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 method for training a speaker recognition network model. The method comprises the steps of acquiring the ternary group of i utterance from the training data set, and inputting the ternary group of the i utterance into a convolutional neural network, the convolutional neural network carrying out characteristic extraction on the ternary group of the i utteranceto obtain a ternary group of the i utterance characteristic and inputting into the linear neural network; inputting the first identity vector information of the first speaker and the second identity vector information of the second speaker into a linear neural network for fusion processing, so as to obtain the fused ternary group of the i utterance; and calculating a ternary group loss according to the ternary group of the i utterance so as to adjust the network model. The speaker recognition network model obtained by the embodiment of the invention can realize the recognition function of speakers more accurately, and has the lowest error rate.

Description

technical field [0001] The invention relates to the technical field of artificial intelligence, in particular to a speaker recognition network model training method, speaker recognition method and system. Background technique [0002] Speaker recognition technology, as a direction of biometric recognition, has received rapid development and widespread attention in both theoretical and application fields. In the classic speaker recognition algorithm, the defects of the classic algorithm are analyzed from the theory and practical application, and the speaker recognition algorithm based on i-vector is introduced. In the i-vector framework, each frame of speech The i-vector low-dimensional representation is extracted from the data, and the low-dimensional representations of all frames are averaged to obtain the speaker representation. [0003] However, the inventor found in the process of implementing the present invention that, in the case of short registration sentences, i-ve...

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): G10L17/04G10L17/18
CPCG10L17/04G10L17/18
Inventor 钱彦旻黄子砾王帅
Owner AISPEECH CO LTD
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