Voice retrieval method and system based on audio fingerprints

Abstract

The invention relates to a voice retrieval method and system based on audio fingerprints. The method comprises the following steps: extracting Mel frequency cepstrum coefficient (MFCC) features and linear prediction cepstrum coefficient (LPCC) features of original voice with the duration of 20s; performing feature combination processing on the MFCC features and the LPCC features, and determining acombined feature matrix; performing column dimension reduction on the combined feature matrix based on an information entropy feature dimension reduction method, and determining a feature matrix after column dimension reduction; based on an energy-based feature dimension reduction method, performing row dimension reduction on the feature matrix after column dimension reduction, and determining afeature matrix after row dimension reduction; constructing an audio fingerprint database according to the feature matrix subjected to row dimension reduction; and performing matching retrieval on theto-be-queried voice segment and the audio fingerprint in the audio fingerprint library by using a normalized Hamming distance algorithm. According to the invention, the retrieval efficiency and retrieval precision of the long voice segment and the retrieval robustness of the audio fingerprint can be improved.

Description

technical field [0001] The invention relates to the field of audio retrieval, in particular to a voice retrieval method and system based on audio fingerprints. Background technique [0002] With the explosive growth of the number of digital audio on the Internet, high-speed retrieval in audio big data has become an urgent problem to be solved. Audio fingerprint retrieval technology uses short audio fingerprint data instead of audio itself for retrieval, which can effectively improve the efficiency of audio retrieval, but the amount of fingerprint data corresponding to audio big data is also quite large, and traditional audio fingerprint retrieval methods have been difficult to meet the requirements of audio big data. Fast and accurate retrieval requirements in the environment. Therefore, audio retrieval technology has been widely concerned by many researchers. [0003] At present, scholars have proposed many methods in audio fingerprinting, feature extraction, dimensionali...

AI Technical Summary

Problems solved by technology

[0006] The purpose of the present invention is to provide a voice retrieval method and system based on audio fingerprints, to solve the problems of low retrieval efficiency and poor retrieval robustness of existing audio fingerprint methods for long speech segments

Images