A method and system for storing and retrieving digital audio fingerprint big data

A technology of big data storage and audio fingerprint, which is applied in the direction of audio data retrieval, digital data information retrieval, audio data indexing, etc. It can solve the problems of not being able to use big data, reduce the amount of calculation, time consumption, and time extension, etc., and achieve saving analysis Calculation process, effect of saving calculation and time cost

Active Publication Date: 2021-06-25
成都潜在人工智能科技有限公司
View PDF4 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0007] The first purpose of the present invention is to provide a method for storing and retrieving large data of digital audio fingerprints in view of the drawbacks of the prior art, such as prolonged time-existence and incapability of big data, which can store massive amounts of data by adopting ...

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
  • A method and system for storing and retrieving digital audio fingerprint big data
  • A method and system for storing and retrieving digital audio fingerprint big data
  • A method and system for storing and retrieving digital audio fingerprint big data

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0033] Refer figure 1 A method of digital audio fingerprint large data storage retrieval, mainly including two steps of fingerprint library 300 establishment and fingerprint, establishing and fingerprint retrieval by fingerprint library 300, can quickly extract and analyze the first N first N first The information of the song fragment realizes the optimization of the search, which can save the calculation process to improve the identification efficiency of the audio.

[0034] The establishment of the fingerprint library 300 includes extracting audio fingerprints from a known type of audio file and generating a time point corresponding to the audio fingerprint, stores audio fingerprints and corresponding time points in a file in a file, with audio Identification information adds as a file name; store audio fingerprints, time points, and filenames into the HBase storage system, with audio fingerprint as a row key, time point as the column name, fragmentation file name as the corresp...

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 method and system for storing and retrieving digital audio fingerprint big data. The time points are stored in the file in the form of fragmented storage, and the audio identification information plus the index is used as the file name; the audio fingerprint, time point and file name are stored in the distributed columnar storage system, and the audio fingerprint is used as the row key and time point. As the column name and the file name of the fragment as the corresponding value; extract the audio fingerprint from the audio file to be recognized, retrieve the fragment file name containing the audio fingerprint of the audio file to be recognized from the distributed columnar storage system, and obtain The top N fragments with the most occurrences, where N is a preset positive integer. The invention adopts the distributed column storage system for storage and fast retrieval, which can store massive information, quickly extract segments, and improve the efficiency of audio recognition.

Description

Technical field [0001] The present invention belongs to the technical field of audio processing, and is specifically related to a method and system of digital audio fingerprint large data storage retrieval. Background technique [0002] The current popular music listening to songs, 曲, etc. is basically the extraction of audio unique feature amount, in order to improve the accuracy of the identification, the audio feature is required as much as possible. Usually, the audio has thousands of feature amounts. When the digital audio reaches a certain amount, the audio feature requires a large database to store, resulting in a rapid decline in the database query speed. Most of the identification process is in the database query, so the design of the fingerprint database is critical. [0003] The Phillips Audio Fingerprint Algorithm proposes that a fingerprint can produce a fingerprint, a fingerprint consisting of 256 subfingerprints, and if a audio is generated, it is very large. Phill...

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): G06F16/683G06F16/61
CPCG06F16/61G06F16/683
Inventor 尹学渊王东明
Owner 成都潜在人工智能科技有限公司
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