High robustness audio fingerprint identification method and system

An audio fingerprint, high robustness technology, applied in speech recognition, devices with speech recognition, speech analysis, etc., can solve the problem that speech recognition technology cannot be well adapted to intelligent outbound call applications.

Active Publication Date: 2018-08-14
BEIJING RONGLIAN YITONG INFORMATION TECH CO LTD
View PDF12 Cites 6 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0005] The invention provides a highly robust audio fingerprint recognition method and system to solve the defect th

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
  • High robustness audio fingerprint identification method and system
  • High robustness audio fingerprint identification method and system
  • High robustness audio fingerprint identification method and system

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0071] The preferred embodiments of the present invention will be described below in conjunction with the accompanying drawings. It should be understood that the preferred embodiments described here are only used to illustrate and explain the present invention, and are not intended to limit the present invention.

[0072] For a highly robust audio fingerprint recognition method provided by an embodiment of the present invention, see figure 1 As shown, including steps 101-105:

[0073] Step 101: Obtain audio data to be identified, and perform preprocessing on the audio data to be identified to remove special signals, which include one or more of ringing tone, color ring tone, busy tone, and silence.

[0074] In the embodiment of the present invention, the audio data to be identified may specifically be audio data related to the calling tone or the called tone; taking the called tone as an example, there are many types of the called tone, generally at least 30 Various, by remov...

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 high robustness audio fingerprint identification method and system. The method comprises the following steps audio frequency data to be identified is obtained and subjected topreprocessing operation, preprocessed audio data to be identified is orderly subjected to frequency domain transformation and Bark domain transformation, all sub-band energy is used as primitive characters of the audio data to be identified, the primitive characters are subjected to correcting operation, corrected primitive characters are used as robustness characteristics of the audio data to beidentified, audio fingerprint modeling operation is performed according to the robustness characteristics of the audio data to be identified, audio fingerprints to be identified corresponding to theaudio data to be identified are generated, a preset audio fingerprint database is loaded, the audio fingerprints to be identified are matched with standard audio fingerprints in the audio fingerprintdatabase, and the audio fingerprints to be identified are identified. According to the method, the robustness characteristics are used to generate the audio fingerprints to be identified which are then matched with the standard audio fingerprints, robustness of identification processes can be improved, and accuracy of identification results can be improved.

Description

technical field [0001] The invention relates to the technical field of audio recognition, in particular to a highly robust audio fingerprint recognition method and system. Background technique [0002] At present, the audio fingerprint technology extracts the invariant features in the audio signal and uses them as a unique identifier to describe the signal. This feature is called an audio fingerprint. Audio fingerprint, as the core algorithm of automatic content identification technology, has been widely used in song identification, content monitoring, content deduplication, file identification and other fields. [0003] Audio fingerprint technology has the characteristics of content-based, less fingerprint data, and certain robustness against attacks, so it can better solve the problem of audio retrieval and matching. After the fingerprint technology was proposed, it has developed rapidly, and many technical solutions have been proposed, and good commercial applications ha...

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): G10L15/02G10L15/06G10L25/51H04M3/51
CPCG10L15/02G10L15/06G10L25/51H04M3/51H04M2250/74
Inventor 曾国卿
Owner BEIJING RONGLIAN YITONG INFORMATION TECH 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
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