Speaker identification method and system

A speaker identification and speaker technology, applied in the field of speaker identification, can solve problems such as low speaker accuracy and channel noise interference

Pending Publication Date: 2021-07-06
SHANDONG NORMAL UNIV
View PDF5 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

The speaker's speech features extracted by the feature extraction model often have large channel noise interference, which cannot well display the speaker's unique voiceprint features, resulting in low speaker recognition accuracy

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 identification method and system
  • Speaker identification method and system

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0046] In order to solve the problem of greater channel noise interference in the speech characteristics, it is not possible to show the unique sound characteristics of the speaker. Embodiment 1 of the present invention provides a speaker recognition system, the system confirms the network auxiliary extraction. People unique sound characteristics, reduce channel noise interference, assist in improving speaker recognition accuracy.

[0047] The speaker recognition system includes:

[0048] The confirmation module is used to use the confirmation network to analyze the voice signal, extract the voice signal, and confirm whether the voice signal comes from the same speaker; where the confirmation network uses the first training set training, the The first training set includes the first data pair and the second data pair;

[0049] Identification module, used to analyze the sound characteristics of the voice signal using the Identification Network, identify the identity of the speaker ...

Embodiment 2

[0074] Embodiment 2 of the present invention provides a computer device, including a memory and a processor, the processor, and the memory communication, the memory stores program instructions performed by the processor, the processor call Program instructions perform speaker recognition methods, including:

[0075] Using the confirmation network analysis, the voice signal is analyzed, extract the sound line characteristics of the speech signal, and confirm whether the voice signal comes from the same speaker; where the confirmation network uses the first training set training, the first training set includes The first data is pair and the second data pair;

[0076] Using the Identified Network to analyze the sound characteristics of the voice signal, identify the identity of the speaker of the voice signal; wherein the identified network uses a second training set training, the second training set includes speaker's voice segment. Voice characteristics and labels identified by sp...

Embodiment 3

[0080]Embodiment 3 of the present invention provides a computer readable storage medium that stores a computer program that implements a speaker-recognized method when executed by a processor, which includes:

[0081] Using the confirmation network analysis, the voice signal is analyzed, extract the sound line characteristics of the speech signal, and confirm whether the voice signal comes from the same speaker; where the confirmation network uses the first training set training, the first training set includes The first data is pair and the second data pair;

[0082] Using the Identified Network to analyze the sound characteristics of the voice signal, identify the identity of the speaker of the voice signal; wherein the identified network uses a second training set training, the second training set includes speaker's voice segment. Voice characteristics and labels identified by speaker of the voice segment.

[0083] The processor can be a central processing unit CPU, which may a...

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 provides a speaker identification method and system, and belongs to the technical field of speaker identification. The method comprises the steps of analyzing voice signals by using a confirmation network, extracting voiceprint features of the voice signals, and confirming whether the voice signals are from the same speaker or not; and analyzing the voiceprint features of the voice signals by using an identification network, and identifying the identity of a speaker of the voice signals. According to the method, specific voiceprint features of the speaker are extracted, channel noise interference is reduced, and the identification accuracy of the speaker is improved; the speaker confirmation network and the speaker identification network can assist each other by adopting a multi-task learning form, so that the confirmation effect and the identification effect are improved; a human brain thinking mode is simulated by combining a speaker confirmation technology, and identification is carried out by combining the confirmation technology under the condition that the number of speakers is large and the identification difficulty is high; and through the simulation application of the human brain thinking model, the intelligence of the algorithm is improved, and the identification ability of the model under the condition of high difficulty is enhanced.

Description

Technical field [0001] The present invention relates to the field of speaker recognition, and in particular to a speaker recognition method and system that improves speaker recognition accuracy. Background technique [0002] The speaker identifies a wide application prospect, which can be widely used in the fields of security, social security, and criminal investigation. The speaker identifies the confirmation and speaker recognition of two major technologies. The speaker confirms that it refers to the speech to confirm whether the current speaker is a registered person who has been registered, or determines whether the two speech comes from the same person. The speaker confirmed that it was a class of classification technology. The speaker recognition is a multi-class classification technology to discriminate the identity of the speaker according to people's voice. [0003] The implementation method of speaker recognition is usually a feature extraction model to extract speaker'...

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): G10L17/04G10L17/18G10L25/24
CPCG10L17/04G10L17/18G10L25/24
Inventor 冷严李文静赵玮玮孙建德唐勇齐广慧王荣燕李登旺万洪林
Owner SHANDONG 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