Voiceprint-recognition-based channel matching method and device

A voiceprint recognition and channel technology, which is applied in the channel matching method of voiceprint recognition and its device field, can solve the problems of large amount of calculation, difficulty in obtaining recognition effect, and large amount of training data, so as to solve the problem of channel mismatch and reduce complexity degree, good recognition effect

Inactive Publication Date: 2017-12-15
TSINGHUA UNIV
View PDF5 Cites 9 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Taking JFA as an example, the amount of training data is required to be very large, and the amount of computation during testing is also very large. It is often difficult to obtain good recognition results in practical applications.

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-recognition-based channel matching method and device
  • Voiceprint-recognition-based channel matching method and device

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0066] A channel matching method and device for voiceprint recognition proposed by the present invention are described in detail as follows with reference to the accompanying drawings.

[0067] A kind of channel matching method for voiceprint recognition proposed by the present invention, its process is as follows figure 1 As shown, the method includes: a data acquisition and reading stage, a speech encoding stage, a channel error bit simulation stage, and a speech decoding stage;

[0068] 1) Data acquisition and reading stage, including the following steps:

[0069] 1-a) collecting and reading original voice data, wherein the original voice data is in WAV format;

[0070] 1-b) remove the file header of the original voice data according to the WAV format standard, and obtain the pure voice data block;

[0071] 2) speech coding stage, comprises the following steps:

[0072] 2-a) Select the voice communication mode to be simulated according to the original voice data, the voi...

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, which belongs to the fields of voice recognition and voice communication, provides a voiceprint-recognition-based channel matching method and device. According to the method, voice data are collected; according to a needed simulated communication mode, voice coding is carried out on the voice data to obtain compressed voice data; error code processing is carried out on the compressed voice data according to an error code rate of channel simulation in a corresponding communication mode to obtain channel simulation voice data; and then voice decoding is carried out on the voice data to obtain voices in a corresponding communication mode. In addition, the device is composed of a voice acquisition and reading module, a voice coding module, a channel error code simulation module, a voice decoding module and a data storage module. Therefore, fixed-phone, VOIP, WeChat-phone, QQ-phone, 2G, 3G, 4G and other voice communication processes can be simulated to obtain training voices having the same channel conditions as the testing voice, so that the channel mismatch problem is solved. The voiceprint-recognition-based channel matching method and device are suitable for meeting the voiceprint recognition application need.

Description

technical field [0001] The invention relates to the fields of speech recognition and speech communication, in particular, a channel matching method and device for voiceprint recognition. technical background [0002] Voiceprint recognition, also known as speaker recognition, is a biometric recognition technology that uses computers to automatically determine the speaker's identity based on voice. According to different application scenarios, there are many classification methods for voiceprint recognition technology: according to whether the voice content is known, voiceprint recognition can be divided into text-related and text-independent. According to different recognition tasks, voiceprint recognition can be divided into speaker identification and speaker confirmation. Voiceprint recognition technology is mainly used in the fields of security monitoring, criminal investigation and justice, and e-commerce. [0003] In recent years, mainstream text-independent speaker re...

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): G10L17/02G10L17/04G10L17/20
CPCG10L17/02G10L17/04G10L17/20
Inventor 梁永立何亮吴晋
Owner TSINGHUA 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