Looking for breakthrough ideas for innovation challenges? Try Patsnap Eureka!

Speaker identification method and device

A speaker recognition and speaker technology, applied in the field of speaker recognition methods and devices, can solve the problems of low efficiency of voice monitoring and achieve the effects of improving efficiency and ensuring public safety

Inactive Publication Date: 2016-01-13
RUN TECH CO LTD BEIJING
View PDF5 Cites 42 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Therefore, in the prior art, the efficiency of the voice monitoring of the artificial listening method is relatively low

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 device
  • Speaker identification method and device
  • Speaker identification method and device

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0024] figure 1 It is a flow chart of a speaker recognition method provided by Embodiment 1 of the present invention. This embodiment is applicable to the situation of recognizing speaker identity information of audio data obtained in voice monitoring, and the method can be executed by a speaker recognition system , the system can be realized by means of software and / or hardware.

[0025] figure 2 is an overall architecture diagram of the speaker recognition system in the speaker recognition method provided by the embodiment of the present invention, as shown in figure 2 As shown, the speaker recognition system includes a data application layer, a service layer, a data layer and a voiceprint collection layer. Among them, the voiceprint collection layer is used to collect the audio data of the speaker or collect voiceprint samples. The collection methods include telecommunications monitoring (such as mobile phones), network monitoring (such as Internet calls, Michat and WeC...

Embodiment 2

[0046] Figure 5 It is a flow chart of a speaker recognition method provided by Embodiment 2 of the present invention. This embodiment is based on Embodiment 1. Embodiment 1 is optimized, adding voice recognition to audio data to obtain voice text and extracting voice text. The operation of the keyword, and then optimize the search for the voiceprint sample with the voiceprint feature in the voiceprint database to search for the voiceprint sample with the keyword in the voiceprint database according to the keyword, and calculate the voiceprint feature Based on the similarity with the voiceprint features in the voiceprint samples, the voiceprint samples whose similarity exceeds the set threshold are extracted. The method specifically includes the following steps:

[0047] Step 510, collecting audio data of the speaker.

[0048] Step 520, performing speech recognition on the audio data to obtain speech text.

[0049] Speech recognition is a high technology that allows machine...

Embodiment 3

[0069] Figure 6 It is a schematic structural diagram of a speaker recognition device provided in Embodiment 3 of the present invention. Such as Figure 6 As shown, the speaker recognition device described in this embodiment includes: an audio data collection module 610 , a voiceprint feature extraction module 620 , a voiceprint sample search module 630 and an identity information determination module 640 .

[0070] Wherein, the audio data collection module 610 is used for collecting the audio data of the speaker;

[0071] The voiceprint feature extraction module 620 is used to extract the voiceprint feature of the audio data;

[0072] The voiceprint sample search module 630 is used to search for voiceprint samples having the voiceprint characteristics in the voiceprint database, and the voiceprint database stores the correspondence between identity information and voiceprint samples;

[0073] The identity information determining module 640 is configured to determine the id...

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 discloses a speaker identification method and a device. The speaker identification method comprises steps of collecting audio frequency data of a speaker, extracting voiceprint characteristics of the audio frequency data, searching a voiceprint sample having the voiceprint characteristic from a voiceprint database, wherein the voiceprint database stores a corresponding relation between identity information and the voiceprint sample, and determining the identity information of the speaker according to the voiceprint sample and the corresponding relation between the voiceprint sample and the identity information. The invention improves the efficiency of voice monitoring and provides the guarantee to the common safety.

Description

technical field [0001] Embodiments of the present invention relate to voice monitoring technology, and in particular to a speaker recognition method and device. Background technique [0002] With the advent of the information age, voice monitoring has become one of the important technical means in the field of public security. [0003] In the prior art, manual listening is mainly used for voice monitoring. With the massive explosion of Internet data volume, the manual listening method has the problems of heavy online listening workload, low work efficiency, and insufficient listening personnel. become increasingly prominent, resulting in the inability to track and detect a large number of illegal and criminal clues in the audio data in advance. Especially for cases with wide geographical distribution and diverse language distribution, there are very few staff members who are familiar with small languages ​​and various dialects, resulting in a backlog of data. Therefore, in...

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): G10L17/02G10L17/14
Inventor 王旭东
Owner RUN TECH CO LTD BEIJING
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Patsnap Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Patsnap Eureka Blog
Learn More
PatSnap group products

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic, Popular Technical Reports.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com