Deep-learning-based automatic audio annotation method

Abstract

The invention relates to an audio annotation method, in particular to a deep-learning-based automatic audio annotation method. The deep-learning-based automatic audio annotation method comprises the following steps that original audio files are input, and by means of audio preprocessing, multiple original sound spectrograph segments are obtained; the original sound spectrograph segments are inputinto a convolutional neural network for training, and a deep-learning model is built; to-be-annotated audio files are input, and by means of audio preprocessing, multiple to-be-annotated sound spectrograph segments are obtained; on the basis of the deep-learning model, the to-be-annotated sound spectrograph segments are subjected to audio annotation. Accordingly, the convolutional neural network is utilized for training an audio deep-learning network, and the automatic audio annotation method is realized; compared with a traditional manual annotation mode, the annotation accuracy is improved,and the audio annotation efficiency is improved.

Description

technical field [0001] The present invention relates to an audio labeling method, in particular to an audio automatic labeling method based on deep learning. Background technique [0002] The structural representation of audio is an important issue in MIR (Music Information Retrieval), which mainly extracts features from the audio signal itself to achieve audio retrieval. The traditional way of relying on experts to extract timbre, melody, and rhythm cannot fully describe the audio details, cannot realize automatic labeling, and has a low accuracy rate. Contents of the invention [0003] The purpose of the present invention is to overcome the above-mentioned deficiencies in the prior art, and provide a method for using a convolutional neural network to train an audio deep learning network, construct a deep learning model, and use a maximum voting algorithm to realize automatic audio labeling. [0004] In order to realize the above-mentioned purpose of the invention, the p...

AI Technical Summary

Problems solved by technology

The traditional method of relying on experts to extract timbre, melody, and rhythm cannot fully describe the audio details, cannot realize automatic labeling, and has a low accuracy rate

Images