Sample-level Deep Convolutional Neural Networks for Music Auto-tagging Using Raw Waveforms

Abstract

Recently, the end-to-end approach that learns hierarchical representations from raw data using deep convolutional neural networks has been successfully explored in the image, text and speech domains. This approach was applied to musical signals as well but has been not fully explored yet. To this end, we propose sample-level deep convolutional neural networks which learn representations from very small grains of waveforms (e.g. 2 or 3 samples) beyond typical frame-level input representations. Our experiments show how deep architectures with sample-level filters improve the accuracy in music auto-tagging and they provide results comparable to previous state-of-the-art performances for the Magnatagatune dataset and Million Song Dataset. In addition, we visualize filters learned in a sample-level DCNN in each layer to identify hierarchically learned features and show that they are sensitive to log-scaled frequency along layer, such as mel-frequency spectrogram that is widely used in music classification systems.

7 pages, Sound and Music Computing Conference (SMC), 2017

References in corpus (4)

• Very Deep Convolutional Networks for Large-Scale Image Recognition
• WaveNet: A Generative Model for Raw Audio
• Convolutional Recurrent Neural Networks for Music Classification
• Applying Topological Persistence in Convolutional Neural Network for Music Audio Signals

Cited by in corpus (23)

• Deep Learning for Audio Signal Processing
• A Survey of Sound Source Localization with Deep Learning Methods
• VATT: Transformers for Multimodal Self-Supervised Learning from Raw Video, Audio and Text
• Neonatal seizure detection from raw multi-channel EEG using a fully convolutional architecture
• Rethinking CNN Models for Audio Classification
• End-to-end learning for music audio tagging at scale
• A Tutorial on Deep Learning for Music Information Retrieval
• Investigating the Impact of CNN Depth on Neonatal Seizure Detection Performance
• Sample-level CNN Architectures for Music Auto-tagging Using Raw Waveforms
• RawNet: Advanced end-to-end deep neural network using raw waveforms for text-independent speaker verification
• On the performance of residual block design alternatives in convolutional neural networks for end-to-end audio classification
• audioLIME: Listenable Explanations Using Source Separation
• Large-Scale MIDI-based Composer Classification
• DLR : Toward a deep learned rhythmic representation for music content analysis
• One Deep Music Representation to Rule Them All? : A comparative analysis of different representation learning strategies
• Multi-Level and Multi-Scale Feature Aggregation Using Sample-level Deep Convolutional Neural Networks for Music Classification
• A Feature Learning Siamese Model for Intelligent Control of the Dynamic Range Compressor
• The Effects of Noisy Labels on Deep Convolutional Neural Networks for Music Tagging
• Towards Deep Modeling of Music Semantics using EEG Regularizers
• Instrument-Independent Dastgah Recognition of Iranian Classical Music Using AzarNet
• J-Net: Randomly weighted U-Net for audio source separation
• Multi-scale Embedded CNN for Music Tagging (MsE-CNN)
• An approach to hummed-tune and song sequences matching