Eureka AIR delivers breakthrough ideas for toughest innovation challenges, trusted by R&D personnel around the world.

Digital string voice processing method and device thereof

A voice processing and digital string technology, applied in voice analysis, instruments, etc., can solve problems such as poor voiceprint recognition effect, insufficient stability and accuracy of digital voiceprint model, etc., to achieve less interference, reduced model parameters, and easy to use strong effect

Active Publication Date: 2019-03-08
IFLYTEK CO LTD
View PDF4 Cites 5 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

The acquisition of digital voiceprint model is the key to digital voiceprint recognition. In the prior art, the acquisition of digital voiceprint model is realized based on the method of full variable factor analysis, but the digital voiceprint model obtained based on the method of full variable factor analysis is not enough. Stable and accurate, which leads to poor voiceprint 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
  • Digital string voice processing method and device thereof
  • Digital string voice processing method and device thereof
  • Digital string voice processing method and device thereof

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0056] The following will clearly and completely describe the technical solutions in the embodiments of the application with reference to the drawings in the embodiments of the application. Apparently, the described embodiments are only some of the embodiments of the application, not all of them. Based on the embodiments in this application, all other embodiments obtained by persons of ordinary skill in the art without making creative efforts belong to the scope of protection of this application.

[0057] In the prior art, most of the methods for determining the voiceprint model through a piece of speech are methods based on full variable factor analysis. Specifically, for a piece of speech, first extract features reflecting the voiceprint information, such as the MelFrequency Cepstrum Coefficient (MelFrequency Cepstrum Coefficient) feature. , MFCC), Perceptual Linear Predictive (Perceptual Linear Predictive, PLP), etc., and then use the Baum-Welch algorithm to calculate the po...

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 digital string voice processing method and a device thereof. The method includes the following steps: acquiring a target digital string voice; determining a model based on theentire target digital string voice and a pre-established identity vector, determining a target digital identity vector corresponding to each digit in the target digital string voice, and constitutinga digital voiceprint model corresponding to the target digital string voice by all target digital identity vectors, wherein an identity vector determination model is obtained by using training of thedigital string voice, and the digital voiceprint model contains the structured information for training the digital strings in digital string voice. The digital string voice processing method can determine the stable and accurate digital voiceprint model.

Description

technical field [0001] The present application relates to the technical field of voiceprint recognition, in particular to a digital string voice processing method and device. Background technique [0002] Voiceprint recognition technology, also known as speaker recognition technology, is a technology that uses human voice to detect the speaker's identity. Compared with other biometric technologies, voiceprint recognition technology uses voice signals for identity verification. It has the characteristics of low cost, easy collection, easy storage, difficult to imitate, and friendly interaction. It can also be remotely operated by telephone or network. Therefore, voiceprint recognition technology has good and broad application prospects in many fields such as security, military affairs, economy, and life. [0003] According to the requirements for voice data, voiceprint recognition can be divided into two categories: text-related and text-independent. The former requires the...

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): G10L17/04G10L17/08G10L17/18
CPCG10L17/04G10L17/08G10L17/18
Inventor 闫杰李晋方昕
Owner IFLYTEK 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
Eureka Blog
Learn More
PatSnap group products