Select Page

136 Free Scientific Articles, Thesis and Reports on Deep Learning for Music

136 Free Scientific Articles, Thesis and Reports on Deep Learning for Music
Deep learning is a type of machine learning and artificial intelligence (AI) that imitates the way humans gain certain types of knowledge. Deep learning is an important element of data science, which includes statistics and predictive modeling. As of late, deep learning is gaining much popularity due to it’s supremacy in terms of accuracy when trained with huge amount of data, encouraging software industries to move towards integrating such technology into their development and production cycle. Several music software programs have been developed that use AI to produce music. Artificial intelligence also drives the so-called interactive composition technology, wherein a computer composes music in response to the performance of a live musician. AI might allow more people to make music because it’s now much easier to make a professional sounding single using just even your phone than it was 10 or 20 years ago. At the moment, AI is like a tool. But in the near future, it could be more of a co-creator.

Over the last several years, a new area of research called deep learning has taken the machine learning community by storm, delivering very promising results in all areas of speech and image recognition. However, one missing link is the lack of an accessible and easy-to-use open-source deep learning library for the music and/or audio research community. In this post we will introduce you to scientific articles, thesis and reports that use deep learning approaches applied to music. The documents are generally in PDF formats, sorted by years and paired with source codes if they’re available.

Deep Learning for Music

  1. The representation of pitch in a neural net model of chord classification (1989)
  2. Algorithms for music composition by neural nets: Improved CBR paradigms (1989)
  3. A connectionist approach to algorithmic composition (1989)
  4. Neural network music composition by prediction: Exploring the benefits of psychoacoustic constraints and multi-scale processing (1994)
  5. Automatic source identification of monophonic musical instrument sounds (1995)
  6. Neural network based model for classification of music type (1995)
  7. Recognition of music types (1998)
  8. Multi-phase learning for jazz improvisation and interaction (2001)
  9. A supervised learning approach to musical style recognition (2002)
  10. Finding temporal structure in music: Blues improvisation with LSTM recurrent networks (2002)
  11. Neural networks for note onset detection in piano music (2002)
  12. Unsupervised feature learning for audio classification using convolutional deep belief networks (2009)
  13. Audio musical genre classification using convolutional neural networks and pitch and tempo transformations (2010)
  14. Automatic musical pattern feature extraction using convolutional neural network (2010)
  15. Rethinking automatic chord recognition with convolutional neural networks (2012)
  16. Moving beyond feature design: Deep architectures and automatic feature learning in music informatics (2012)
  17. Local-feature-map integration using convolutional neural networks for music genre classification (2012)
  18. Learning sparse feature representations for music annotation and retrieval (2012)
  19. Multiscale approaches to music audio feature learning (2013)
  20. Musical onset detection with convolutional neural networks (2013)
  21. Deep content-based music recommendation (2013)
  22. The munich LSTM-RNN approach to the MediaEval 2014 Emotion In Music task (2014)
  23. End-to-end learning for music audio (2014)
  24. Deep learning for music genre classification (2014)
  25. From music audio to chord tablature: Teaching deep convolutional networks to play guitar (2014)
  26. Boundary detection in music structure analysis using convolutional neural networks (2014)
  27. Auralisation of deep convolutional neural networks: Listening to learned features (2015) – Code
  28. Downbeat tracking with multiple features and deep neural networks (2015)
  29. Music boundary detection using neural networks on spectrograms and self-similarity lag matrices (2015)
  30. Classification of spatial audio location and content using convolutional neural networks (2015)
  31. Deep learning, audio adversaries, and music content analysis (2015)
  32. Deep learning and music adversaries (2015) – Code
  33. Singing voice detection with deep recurrent neural networks (2015)
  34. Automatic instrument recognition in polyphonic music using convolutional neural networks (2015)
  35. A software framework for musical data augmentation (2015)
  36. A deep bag-of-features model for music auto-tagging (2015)
  37. Music-noise segmentation in spectrotemporal domain using convolutional neural networks (2015)
  38. Musical instrument sound classification with deep convolutional neural network using feature fusion approach (2015)
  39. Environmental sound classification with convolutional neural networks (2015)
  40. Exploring data augmentation for improved singing voice detection with neural networks (2015) – Code
  41. Singer traits identification using deep neural network (2015)
  42. A hybrid recurrent neural network for music transcription (2015)
  43. An end-to-end neural network for polyphonic music transcription (2015)
  44. Deep karaoke: Extracting vocals from musical mixtures using a convolutional deep neural network (2015)
  45. Folk music style modelling by recurrent neural networks with long short term memory units (2015) – Code

Other Related Posts

  1. 126 Free Artificial Intelligence (AI) Courses, Ebooks, Videos And Papers – 2021
    This is a curated list of free Artificial Intelligence (AI) courses, ebooks, videos and papers pointing towards interesting directions and topics that you may be interested in. Some resources may be old, but still applicable to today’s standards of AI implementations. We’ve also included some of our previous compilations of AI ebooks and resources, so feel free to check them out as well.
  2. 42 Most Popular And Downloaded Artificial Intelligence, Logic & Robotics Ebooks – 2016
    One of the biggest compilation (if not the biggest) of free resources & ebooks on Artificial Intelligence, Logics & Robotics out there on the net, with a little bit more focus on AI. Majority of the reading materials are in PDF format, with very generous amount of information, no fewer than a few hundred of pages.
  3. Other free Artificial Intelligence ebooks
  4. Other free Music ebooks
  1. Deep neural network based instrument extraction from music (2015)
  2. A deep neural network for modeling music (2015)
  3. An efficient approach for segmentation, feature extraction and classification of audio signals (2016)
  4. Towards playlist generation algorithms using RNNs trained on within-track transitions (2016)
  5. Automatic tagging using deep convolutional neural networks (2016)
  6. Automatic chord estimation on seventhsbass chord vocabulary using deep neural network (2016)
  7. DeepBach: A steerable model for Bach chorales generation (2016) – Code
  8. Deep learning for music (2016)
  9. Learning temporal features using a deep neural network and its application to music genre classification (2016)
  10. On the potential of simple framewise approaches to piano transcription (2016)
  11. Feature learning for chord recognition: The deep chroma extractor (2016) – Code
  12. A fully convolutional deep auditory model for musical chord recognition (2016)
  13. A deep bidirectional long short-term memory based multi-scale approach for music dynamic emotion prediction (2016)
  14. Event localization in music auto-tagging (2016) – Code
  15. Deep convolutional networks on the pitch spiral for musical instrument recognition (2016) – Code
  16. SampleRNN: An unconditional end-to-end neural audio generation model (2016) – Code
  17. Robust audio event recognition with 1-max pooling convolutional neural networks (2016)
  18. Experimenting with musically motivated convolutional neural networks (2016) – Code
  19. Singing voice melody transcription using deep neural networks (2016)
  20. Singing voice separation using deep neural networks and F0 estimation (2016) – Code
  21. Learning to pinpoint singing voice from weakly labeled examples (2016)
  22. Analysis of time-frequency representations for musical onset detection with convolutional neural network (2016)
  23. Music transcription modelling and composition using deep learning (2016) – Code
  24. Deep convolutional neural networks and data augmentation for acoustic event detection (2016) – Code
  25. Gabor frames and deep scattering networks in audio processing (2017)
  26. Vision-based detection of acoustic timed events: A case study on clarinet note onsets (2017)
  27. Deep learning techniques for music generation – A survey (2017)
  28. JamBot: Music theory aware chord based generation of polyphonic music with LSTMs (2017) – Code
  29. XFlow: 1D <-> 2D cross-modal deep neural networks for audiovisual classification (2017)
  30. Machine listening intelligence (2017)
  31. Monoaural audio source separation using deep convolutional neural networks (2017) – Code
  32. Deep multimodal network for multi-label classification (2017)
  33. A tutorial on deep learning for music information retrieval (2017) – Code
  34. A comparison on audio signal preprocessing methods for deep neural networks on music tagging (2017) – Code
  35. Transfer learning for music classification and regression tasks (2017) – Code
  36. Convolutional recurrent neural networks for music classification (2017) – Code
  37. An evaluation of convolutional neural networks for music classification using spectrograms (2017)
  38. Large vocabulary automatic chord estimation using deep neural nets: Design framework, system variations and limitations (2017)
  39. Basic filters for convolutional neural networks: Training or design? (2017)
  40. Ensemble Of Deep Neural Networks For Acoustic Scene Classification (2017)
  41. Robust downbeat tracking using an ensemble of convolutional networks (2017)
  42. Music signal processing using vector product neural networks (2017)
  43. Transforming musical signals through a genre classifying convolutional neural network (2017)
  44. Audio to score matching by combining phonetic and duration information (2017) – Code
  1. Interactive music generation with positional constraints using anticipation-RNNs (2017)
  2. Deep rank-based transposition-invariant distances on musical sequences (2017)
  3. GLSR-VAE: Geodesic latent space regularization for variational autoencoder architectures (2017)
  4. Deep convolutional neural networks for predominant instrument recognition in polyphonic music (2017)
  5. CNN architectures for large-scale audio classification (2017)
  6. DeepSheet: A sheet music generator based on deep learning (2017)
  7. Talking Drums: Generating drum grooves with neural networks (2017)
  8. Music emotion recognition via end-to-end multimodal neural networks (2017)
  9. Chord label personalization through deep learning of integrated harmonic interval-based representations (2017)
  10. End-to-end musical key estimation using a convolutional neural network (2017)
  11. MediaEval 2017 AcousticBrainz genre task: Multilayer perceptron approach (2017)
  12. Classification-based singing melody extraction using deep convolutional neural networks (2017)
  13. Multi-level and multi-scale feature aggregation using pre-trained convolutional neural networks for music auto-tagging (2017)
  14. Multi-level and multi-scale feature aggregation using sample-level deep convolutional neural networks for music classification (2017) – Code
  15. Sample-level deep convolutional neural networks for music auto-tagging using raw waveforms (2017)
  16. A SeqGAN for Polyphonic Music Generation (2017) – Code
  17. Harmonic and percussive source separation using a convolutional auto encoder (2017)
  18. Stacked convolutional and recurrent neural networks for music emotion recognition (2017)
  19. Monaural Singing Voice Separation with Skip-Filtering Connections and Recurrent Inference of Time-Frequency Mask (2017) – Code
  20. Generating data to train convolutional neural networks for classical music source separation (2017) – Code
  21. Monaural score-informed source separation for classical music using convolutional neural networks (2017) – Code
  22. A deep multimodal approach for cold-start music recommendation (2017) – Code
  23. Melody extraction and detection through LSTM-RNN with harmonic sum loss (2017)
  24. Representation learning of music using artist labels (2017)
  25. Toward inverse control of physics-based sound synthesis (2017) – Code
  26. DNN and CNN with weighted and multi-task loss functions for audio event detection (2017)
  27. End-to-end learning for music audio tagging at scale (2017) – Code
  28. Designing efficient architectures for modeling temporal features with convolutional neural networks (2017) – Code
  29. Timbre analysis of music audio signals with convolutional neural networks (2017) – Code
  30. Deep learning for event detection, sequence labelling and similarity estimation in music signals (2017)
  31. Music feature maps with convolutional neural networks for music genre classification (2017)
  32. Automatic drum transcription for polyphonic recordings using soft attention mechanisms and convolutional neural networks (2017) – Code
  33. Adversarial semi-supervised audio source separation applied to singing voice extraction (2017)
  34. Invariances and data augmentation for supervised music transcription (2017) – Code
  35. A hybrid DSP/deep learning approach to real-time full-band speech enhancement (2017) – Code
  36. Recognition and retrieval of sound events using sparse coding convolutional neural network (2017)
  37. A two-stage approach to note-level transcription of a specific piano (2017)
  38. Reducing model complexity for DNN based large-scale audio classification (2017)
  39. Audio spectrogram representations for processing with convolutional neural networks (2017) – Code
  40. Unsupervised feature learning based on deep models for environmental audio tagging (2017)
  41. Attention and localization based on a deep convolutional recurrent model for weakly supervised audio tagging (2017) – Code
  42. A study on LSTM networks for polyphonic music sequence modelling (2017)
  43. MuseGAN: Multi-track sequential generative adversarial networks for symbolic music generation and accompaniment (2018) – Code
  44. Music transformer: Generating music with long-term structure (2018)
  45. Music theory inspired policy gradient method for piano music transcription (2018)
  46. Enabling factorized piano music modeling and generation with the MAESTRO dataset (2019) – Code
  47. Generating Long Sequences with Sparse Transformers (2019) – Code