Speaker gender automatic recognition method and system based on deep self-coding network

A self-encoding network, automatic identification technology, applied in the field of speaker gender automatic identification methods and systems, to achieve the effect of improving accuracy, reducing computational complexity, and reducing complexity

Active Publication Date: 2019-03-29
HUAZHONG NORMAL UNIV
View PDF10 Cites 12 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0006] In the existing technology based on i-vector, the deep belief network (DBN) is mostly used for model construction, and the deep autoencoder network (SAE) is not used to re-extract features from i-vector and finally complete the classification recognition

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 gender automatic recognition method and system based on deep self-coding network
  • Speaker gender automatic recognition method and system based on deep self-coding network
  • Speaker gender automatic recognition method and system based on deep self-coding network

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0053] In order to make the object, technical solution and advantages of the present invention more clear, the present invention will be further described in detail below in conjunction with the examples. It should be understood that the specific embodiments described here are only used to explain the present invention, not to limit the present invention.

[0054] The invention provides a speaker gender recognition method based on i-vector and deep self-encoding network. In the training phase, the speech signal of the training set is first preprocessed and Mel cepstral coefficient feature extraction is performed, and then a large amount of speech data unrelated to specific speakers and channels is used to train the UBM general background model; based on this UBM and the Mel cepstrum coefficient of a specific speaker Feature extraction i-vector; use the extracted i-vector to train a deep autoencoder network to achieve binary classification of men and women. In the test phase, ...

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 belongs to the technical field of vocal print recognition, and discloses a speaker gender automatic recognition method and system based on deep self-coding network. The method comprisesthe steps that a voice signal training UIBM general background model which is not related to a registered speaker and channel is utilized; i-vector of registered data is extracted; i-vector of testingdata is extracted; a deep self-coding network is trained; mode matching and recognition are conducted, and model evaluation is conducted. The method and the system have the advantages that the deep self-coding network is applied to speaker gender recognition, the powerful learning capability of the deep self-coding network is used for characterizing speaker features of different genders, the re-extraction of the features is achieved, feature dimension is reduced, and therefore the complicity of sorting computation is reduced; the method can be further popularized and used for speaker recognition to try to improve the robustness of a speaker recognition system.

Description

technical field [0001] The invention belongs to the technical field of voiceprint recognition, in particular to a method and system for automatic speaker gender recognition based on a deep self-encoding network. Background technique [0002] At present, the commonly used existing technologies in the industry are as follows: [0003] Speaker gender recognition is a biometric authentication technology that uses gender-specific speaker information contained in voice signals to automatically identify the speaker's gender, similar to speaker recognition (voiceprint recognition). Deep learning simulates the hierarchical structure of the human brain when processing information. In essence, it realizes the layer-by-layer abstraction of features through nonlinear transformation in the form of multiple hidden layer connections, and constructs a mapping from low-level features to high-level concepts, which is more powerful. learning ability. In the field of speech recognition in rec...

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): G10L17/02G10L17/04G10L17/18G10L25/24
CPCG10L17/02G10L17/04G10L17/18G10L25/24
Inventor 王志锋段苏容左明章田元闵秋莎夏丹叶俊民陈迪罗恒姚璜
Owner HUAZHONG NORMAL UNIV
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