Music Retrieval System Based on Audio Fingerprint Features

Abstract

An audio fingerprint feature-based music retrieval system, comprising a preprocessing module, a feature extraction module, a reverse index module and a precise matching module. The preprocessing module primarily conducts conversion, resampling, and filtering of audio signals; the feature extraction module is a representation of an audio file employing audio fingerprint features and selecting the most stable points in the frequency spectrum as feature points via double screening based on a dynamic threshold, and using a pair of points to represent a feature; the reverse index module uses the features as keywords, and establishes a reverse index by the features in a music library, and returns an index result according to the number of the same keywords; the precise matching module combines the timing relationships between audio features and employs improved editing distance as the degree of similarity between two feature sequences, so as to optimize the index result.

Description

technical field [0001] The invention belongs to the technical field of information retrieval, specifically relates to audio signal processing and multimedia information retrieval systems, and further relates to a music retrieval system based on audio fingerprint features. Background technique [0002] Earlier, since music information was unstructured data, its retrieval system generally implemented retrieval based on text description. For example, to retrieve a song in the Internet, search by the name of the song, singer, songwriter, song access format, etc. This method has many disadvantages: the amount of data is getting larger and larger, so the workload of manual annotation is also increasing; audio perception is difficult to express clearly with text annotation; information description has a certain degree of subjectivity. The content-based music retrieval system retrieves the content according to the characteristic parameters of the information itself rather than the ...

AI Technical Summary

Problems solved by technology

This method has many disadvantages: the amount of data is increasing, and the workload of manual annotation is also increasing; audio perception is difficult to express clearly with text annotation; information description has a certain degree of subjectivity

In the case of massive music data, there will be many hash conflicts and it is not applicable. At the same time, the feature performance is not as good as the previous fingerprint feature.

Images