Convolutional neural network-based music signal multi-instrument identification method

Abstract

The invention discloses a convolutional neural network-based music signal multi-instrument identification method. The method comprises the following steps of S1, extracting two features from an inputaudio, wherein the two features comprise a pitch feature matrix and a constant Q transformation matrix based on tone; S2, carrying out classification according to musical instrument groups, includingtubes, strings and percussion music, inputting the constant Q transformation matrix into a primary convolutional neural network to obtain a classification matrix, and inputting the classification matrix into a classifier to obtain a coarse classification result, namely the musical instrument group type; and S3, on the basis of the classification matrix, inputting the classification matrix into a secondary convolutional neural network with an attention network in combination with a pitch matrix to obtain a subdivision result, namely a specific musical instrument, wherein the attention network allocates weights to different harmonic waves. The method is suitable for musical instrument identification tasks in music information retrieval and can be used for the musical instrument identification method in music automatic transcription.

Description

technical field [0001] The invention relates to the technical fields of signal processing, multi-pitch estimation and convolutional neural network, in particular to a multi-instrument recognition method for music signals based on convolutional neural network. Background technique [0002] Identifying instruments in songs has a wide range of applications in Music Information Retrieval (MIR), such as searching for songs with a specific instrument or identifying where an instrument starts and ends in audio. There are many other applications of this technology. For example, music recommendation methods can benefit from modeling users' preferences for certain instruments, and music genre recognition methods can be improved by genre-dependent instrument information; it can also be used in polyphonic music. tasks such as automatic music transcription, playback technique detection, and sound source separation, where pre-tuning the model for the presence of specific instruments may i...

AI Technical Summary

Problems solved by technology

Most of these methods draw on the processing methods of speech signals, without considering the essential characteristics of musical instruments, such as pitch, timbre, etc.

Images