Giter VIP home page Giter VIP logo

awesome-deep-learning-music's Introduction

Deep Learning for Music (DL4M) Awesome

The role of this curated list is to gather scientific articles, thesis and reports that use deep learning approaches applied to music. The list is currently under construction but feel free to contribute to the missing fields and to add other resources. The resources provided here come from my review of the state-of-the-art for my PhD Thesis for which an article is being written. There are already surveys on deep learning for music generation, speech separation and speaker identification. However, these surveys do not cover music information retrieval tasks that are included in this repository.

Table of contents

DL4M summary

Articles, Thesis and Reports Code
An efficient approach for segmentation, feature extraction and classification of audio signals No
Gabor frames and deep scattering networks in audio processing No
Vision-based detection of acoustic timed events: A case study on clarinet note onsets No
Neural net modeling of music No
Deep learning techniques for music generation - A survey No
A supervised learning approach to musical style recognition No
XFlow: 1D <-> 2D cross-modal deep neural networks for audiovisual classification No
Machine listening intelligence No
Deep multimodal network for multi-label classification No
A tutorial on deep learning for music information retrieval GitHub
A comparison on audio signal preprocessing methods for deep neural networks on music tagging GitHub
Text-based LSTM networks for automatic music composition No
Towards playlist generation algorithms using RNNs trained on within-track transitions No
Automatic tagging using deep convolutional neural networks No
Transfer learning for music classification and regression tasks GitHub
Convolutional recurrent neural networks for music classification GitHub
Auralisation of deep convolutional neural networks: Listening to learned features No
An evaluation of convolutional neural networks for music classification using spectrograms No
The munich LSTM-RNN approach to the MediaEval 2014 "Emotion in music" task No
A machine learning approach to musical style recognition No
Automatic chord estimation on seventhsbass chord vocabulary using deep neural network No
Large vocabulary automatic chord estimation using deep neural nets: Design framework, system variations and limitations No
Audio-based music classification with a pretrained convolutional network No
Multiscale approaches to music audio feature learning No
End-to-end learning for music audio No
Basic filters for convolutional neural networks: Training or design? No
Ensemble Of Deep Neural Networks For Acoustic Scene Classification No
Robust downbeat tracking using an ensemble of convolutional networks No
Downbeat tracking with multiple features and deep neural networks No
Music signal processing using vector product neural networks No
Deep learning for music genre classification No
Multi-phase learning for jazz improvisation and interaction No
Recognition of acoustic events using deep neural networks No
Transforming musical signals through a genre classifying convolutional neural network No
Audio to score matching by combining phonetic and duration information GitHub
Musical networks: Parallel distributed perception and performance No
Music boundary detection using neural networks on spectrograms and self-similarity lag matrices No
Deep image features in music information retrieval No
Interactive music generation with positional constraints using anticipation-RNNs No
Deep rank-based transposition-invariant distances on musical sequences No
GLSR-VAE: Geodesic latent space regularization for variational autoencoder architectures No
DeepBach: A steerable model for Bach chorales generation GitHub
Deep convolutional neural networks for predominant instrument recognition in polyphonic music No
CNN architectures for large-scale audio classification No
Classification of spatial audio location and content using convolutional neural networks No
Bayesian meter tracking on learned signal representations No
DeepSheet: A sheet music generator based on deep learning No
Deep learning for music No
From music audio to chord tablature: Teaching deep convolutional networks to play guitar No
Rethinking automatic chord recognition with convolutional neural networks No
Moving beyond feature design: Deep architectures and automatic feature learning in music informatics No
Talking Drums: Generating drum grooves with neural networks No
Music emotion recognition via end-to-end multimodal neural networks No
Learning temporal features using a deep neural network and its application to music genre classification No
On the potential of simple framewise approaches to piano transcription No
Deep learning, audio adversaries, and music content analysis No
Deep learning and music adversaries GitHub
Chord label personalization through deep learning of integrated harmonic interval-based representations No
Feature learning for chord recognition: The deep chroma extractor No
A fully convolutional deep auditory model for musical chord recognition No
End-to-end musical key estimation using a convolutional neural network No
MediaEval 2017 AcousticBrainz genre task: Multilayer perceptron approach No
The representation of pitch in a neural net model of chord classification No
Unsupervised feature learning for audio classification using convolutional deep belief networks No
Multi-level and multi-scale feature aggregation using pre-trained convolutional neural networks for music auto-tagging No
Multi-level and multi-scale feature aggregation using sample-level deep convolutional neural networks for music classification GitHub
Sample-level deep convolutional neural networks for music auto-tagging using raw waveforms No
Singing voice detection with deep recurrent neural networks No
Creation by refinement: A creativity paradigm for gradient descent learning networks No
Algorithms for music composition by neural nets: Improved CBR paradigms No
Audio musical genre classification using convolutional neural networks and pitch and tempo transformations No
Automatic instrument recognition in polyphonic music using convolutional neural networks No
Automatic musical pattern feature extraction using convolutional neural network No
A deep bidirectional long short-term memory based multi-scale approach for music dynamic emotion prediction No
Harmonic and percussive source separation using a convolutional auto encoder No
Event localization in music auto-tagging GitHub
Deep convolutional networks on the pitch spiral for musical instrument recognition GitHub
Neural network based model for classification of music type No
A software framework for musical data augmentation No
Generating data to train convolutional neural networks for classical music source separation GitHub
Monaural score-informed source separation for classical music using convolutional neural networks GitHub
Neural network music composition by prediction: Exploring the benefits of psychoacoustic constraints and multi-scale processing No
Local-feature-map integration using convolutional neural networks for music genre classification No
A deep bag-of-features model for music auto-tagging No
Learning sparse feature representations for music annotation and retrieval No
A convolutional-kernel based approach for note onset detection in piano-solo audio signals No
Multi-label music genre classification from audio, text, and images using deep features GitHub
A deep multimodal approach for cold-start music recommendation GitHub
Melody extraction and detection through LSTM-RNN with harmonic sum loss No
Music-noise segmentation in spectrotemporal domain using convolutional neural networks No
Musical instrument sound classification with deep convolutional neural network using feature fusion approach No
Toward inverse control of physics-based sound synthesis Website
Robust audio event recognition with 1-max pooling convolutional neural networks No
Environmental sound classification with convolutional neural networks No
Score-informed syllable segmentation for a cappella singing voice with convolutional neural networks GitHub
Experimenting with musically motivated convolutional neural networks GitHub
Designing efficient architectures for modeling temporal features with convolutional neural networks GitHub
Timbre analysis of music audio signals with convolutional neural networks GitHub
Monoaural audio source separation using deep convolutional neural networks GitHub
Singing voice melody transcription using deep neural networks No
Singing voice separation using deep neural networks and F0 estimation Website
Improved musical onset detection with convolutional neural networks No
Exploring data augmentation for improved singing voice detection with neural networks GitHub
Learning to pinpoint singing voice from weakly labeled examples No
Deep learning for event detection, sequence labelling and similarity estimation in music signals No
Musical onset detection with convolutional neural networks No
Music feature maps with convolutional neural networks for music genre classification No
Singer traits identification using deep neural network No
A hybrid recurrent neural network for music transcription No
An end-to-end neural network for polyphonic music transcription No
Deep karaoke: Extracting vocals from musical mixtures using a convolutional deep neural network No
Automatic drum transcription for polyphonic recordings using soft attention mechanisms and convolutional neural networks GitHub
Analysis of time-frequency representations for musical onset detection with convolutional neural network No
Note onset detection in musical signals via neural-network-based multi-ODF fusion No
Folk music style modelling by recurrent neural networks with long short term memory units GitHub
Music transcription modelling and composition using deep learning GitHub
Taking the models back to music practice: Evaluating generative transcription models built using deep learning GitHub
Convolutional neural network for robust pitch determination No
Deep convolutional neural networks and data augmentation for acoustic event detection No
A sequential network design for musical applications No
A connectionist approach to algorithmic composition No
Deep neural network based instrument extraction from music No
Boundary detection in music structure analysis using convolutional neural networks No
A hybrid DSP/deep learning approach to real-time full-band speech enhancement GitHub
Deep content-based music recommendation No
Convolutional methods for music analysis No
Extending temporal feature integration for semantic audio analysis No
Recognition and retrieval of sound events using sparse coding convolutional neural network No
A two-stage approach to note-level transcription of a specific piano No
Improving content-based and hybrid music recommendation using deep learning No
Audio spectrogram representations for processing with convolutional neural networks Website
Unsupervised learning of local features for music classification No
Unsupervised feature learning based on deep models for environmental audio tagging No
Surrey-CVSSP system for DCASE2017 challenge task4 GitHub
A study on LSTM networks for polyphonic music sequence modelling Website
Attention and localization based on a deep convolutional recurrent model for weakly supervised audio tagging GitHub
A deep representation for invariance and music classification No
A deep neural network for modeling music No

DL4M details

All details for each article are stored in the corresponding bib entry in dl4m.bib. Each entry has the regular bib field:

  • author
  • year
  • title
  • journal or booktitle

Each entry in dl4m.bib also displays additional information:

  • link - HTML link to the PDF file
  • code - Link to the source code if available
  • archi - Neural network architecture
  • layer - Number of layers
  • task - The proposed tasks studied in the article
  • dataset - The names of the dataset used
  • dataaugmentation - The type of data augmentation technique used
  • time - The computation time
  • hardware - The hardware used
  • note - Additional notes and information
  • repro - Indication to what extent the experiments are reproducible

Code without articles

Statistics and visualisations

  • 138 articles currently referenced.
  • 284 unique researchers currently referenced. List available here: authors.md.
  • Number of articles per year: Number of articles per year

How To Contribute

Contributions are welcome! Please refer to the CONTRIBUTING.md file.

FAQ

How are the articles sorted?

The articles are first sorted by decreasing year (to keep up with the latest news) and then alphabetically by the main author's family name.

Why are preprint from arXiv included in the list?

I want to have exhaustive research and the latest news on DL4M. However, one should take care of the information provided in the articles currently in review. If possible you should wait for the final accepted and peer-reviewed version before citing an arXiv paper. I regularly update the arXiv links to the corresponding published papers when available.

How much can I trust the results published in an article?

The list provided here does not guarantee the quality of the articles. You should either try to reproduce the experiments described or submit a request to ReScience. Use one article's conclusion at your own risks.

Acronyms used

A list of useful acronyms used in deep learning and music is stored in acronyms.md.

Sources

The list of conferences, journals and aggregators used to gather the proposed materials is stored in sources.md.

Contributors

Other useful related lists and resources

awesome-deep-learning-music's People

Contributors

knstmrd avatar sergiooramas avatar ybayle avatar

Stargazers

avatar

Watchers

avatar avatar

Forkers

hannariver

Recommend Projects

  • React photo React

    A declarative, efficient, and flexible JavaScript library for building user interfaces.

  • Vue.js photo Vue.js

    🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.

  • Typescript photo Typescript

    TypeScript is a superset of JavaScript that compiles to clean JavaScript output.

  • TensorFlow photo TensorFlow

    An Open Source Machine Learning Framework for Everyone

  • Django photo Django

    The Web framework for perfectionists with deadlines.

  • D3 photo D3

    Bring data to life with SVG, Canvas and HTML. 📊📈🎉

Recommend Topics

  • javascript

    JavaScript (JS) is a lightweight interpreted programming language with first-class functions.

  • web

    Some thing interesting about web. New door for the world.

  • server

    A server is a program made to process requests and deliver data to clients.

  • Machine learning

    Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.

  • Game

    Some thing interesting about game, make everyone happy.

Recommend Org

  • Facebook photo Facebook

    We are working to build community through open source technology. NB: members must have two-factor auth.

  • Microsoft photo Microsoft

    Open source projects and samples from Microsoft.

  • Google photo Google

    Google ❤️ Open Source for everyone.

  • D3 photo D3

    Data-Driven Documents codes.