Embedded-based open set speaker recognition method and system thereof

A speaker recognition and embedded technology, applied in speech recognition, speech analysis, instruments, etc.

Inactive Publication Date: 2010-07-07
JILIN UNIV
View PDF2 Cites 32 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0014] The present invention provides an embedded open-set speaker recognition method and its system to s

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
  • Embedded-based open set speaker recognition method and system thereof
  • Embedded-based open set speaker recognition method and system thereof
  • Embedded-based open set speaker recognition method and system thereof

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0102] Embodiment 1 Based on the embedded open set speaker recognition method

[0103] 1. Speech signal preprocessing and feature extraction

[0104] First of all, the collected speech signal must be preprocessed and feature extracted to obtain the speech feature parameters of the speaker.

[0105] The object of preprocessing and feature extraction of speech signal is a short-time frame speech signal obtained by AD sampling. In order to ensure real-time performance, it is necessary to complete the preprocessing and feature of the previous frame of speech signal before the end of the sampling of the next frame of speech signal. Extraction; speech signal preprocessing and feature extraction process such as figure 2 As shown, the preprocessing of the speech signal mainly includes small data of the speech signal, peak and saturation processing, windowing, speech enhancement in the frequency domain, and endpoint detection.

[0106] In order to prevent spike interference and too ...

Embodiment 2

[0175] Embodiment 2 is based on the embedded open set speaker recognition system

[0176] The invention discloses an embedded system based on open-set speaker recognition, adopting a single general-purpose digital signal processor (DSP, Digital Signal Processor) as the core processor, and designing embedded hardware and software for the open-set speaker recognition system .

[0177] like Figure 6 As shown, the voice signal processing unit [101] is connected with the voice signal acquisition unit [102], the data storage unit [103], the man-machine interface unit [104], the communication interface unit 106] respectively, and the power management module [105] is connected with the voice The signal processing unit is connected, and the man-machine interface unit includes: a status indicating module, a keyboard module, a display module, and a starting module. The above-mentioned system takes the voice signal processing unit [101] as the core, controls the voice signal acquisitio...

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 relates to an embedded-based open set speaker recognition method and a system thereof, which relates to speaker recognition in the field of voice signal processing. The embedded-based open set speaker recognition method comprises the following steps: firstly, pre-processing and characteristically extracting the voice signals; secondly, taking exercises referencing the speaker voice model; and finally, making the open set mode matching. The recognition system comprises a voice signal processing unit which is respectively connected with a voice signal collecting unit, a data storage unit, a man-machine interface unit and a communication interface unit, a power management module is connected with the voice signal processing unit, and the man-machine interface unit comprises a state indicating module, a keyboard module, a display module and a startup module. The invention has the advantages of suiting different application occasions and raising the security performance of systems. Designing an embedded system performs embedded realization of the open set speaker recognition method. The system has the characteristics of high real-time performance, good recognition performance, low power consumption, low cost, high portability, high popularity, etc.

Description

technical field [0001] The invention relates to speaker recognition in the field of speech signal processing, in particular to a speaker recognition system using an open-set method, in particular to an open-set speaker recognition system realized by an embedded system. Background technique [0002] By consulting relevant materials and related patents, the following patents are mainly cited: [0003] Country name Publication number Publication date [0004] 1. China CN 101350196A 2009.7.19 [0005] 2. China CN 101064043A 2007.10.31 [0006] 3. China CN 1746972A 2006.3.15 [0007] Patent 1 (CN101350196A) application discloses a task-related speaker identity confirmation system-on-chip and a confirmation method thereof. Use the special voice processing chip UniLite400 to design the hardware of the system, and implement the method of speaker confirmation. After the chip UniLite400 receives the voice, it extracts the 12-Vermel frequency cepstrum coefficient and the short...

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): G10L15/02G10L15/06G10L15/28G10L17/00G10L15/07G10L15/30
Inventor 林琳孙晓颖陈建燕学智胡封晔温泉王波魏小丽
Owner JILIN 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