New CRF model segments music into chords with rich features.
problem Harmonic analysis of music segments.
method Semi-Markov Conditional Random Field (semi-CRF) with segment-level features.
result Semi-CRF model performs better than previous approaches.
Dual-track model generates classical piano music better than other methods.
problem Generating inter-dependent piano music.
method Dual-track architecture with various neural network models and music representations.
result Proposed model outperforms other methods in evaluation.
ragamAI uses machine learning to create concert recitals for Carnatic music.
problem Creating a comprehensive listening experience for Carnatic music concerts.
method Playlist and session-based recommender models, leveraging mathematical structure in past concerts.
result ragamAI generates concert recitals that perform 25%-50% better than baseline models.
We introduce MIDI-VAE, a neural network model based on Variational Autoencoders that is capable of handling polyphonic music with multiple instrument tracks, as well as modeling the dynamics of music by incorporating note durations and velocities. We show that MIDI-VAE can perform style transfer on symbolic music by au…
This paper introduces a new large-scale music dataset, MusicNet, to serve as a source of supervision and evaluation of machine learning methods for music research. MusicNet consists of hundreds of freely-licensed classical music recordings by 10 composers, written for 11 instruments, together with instrument/note annot…
Transformer improves pop piano composition by incorporating beat-based structure.
problem Generating expressive pop piano compositions with coherent rhythmic structure.
method Improved data representation for Transformers, incorporating beat-bar-phrase structure.
result Composes pop piano music with better rhythmic structure than existing models.
Deep neural networks improve music phrase segmentation.
problem Automated melodic phrase detection and segmentation in music.
method Adapted various neural network architectures to symbolic music representation, addressing sparse labeling problem.
result CNN-CRF architecture performs best, offering finer segmentation and faster training.
New method for one-shot timbre transfer in music.
problem One-shot timbre transfer in music.
method Self-supervised VQ-VAE extension for disentangled representations.
result Outperforms selected baselines on objective metrics.
Automatic Music Transcription (AMT) is one of the oldest and most well-studied problems in the field of music information retrieval. Within this challenging research field, onset detection and instrument recognition take important places in transcription systems, as they respectively help to determine exact onset times…
End-to-end models classify composers from musical scores.
problem Classifying composers from musical scores using machine learning.
method Pooled and convolutional architectures for feature extraction.
result Models achieve high accuracy on a large corpus of scores.
Model generates coherent polyphonic music using deep reinforcement learning.
problem Creating music that follows musical rules and coherence.
method Deep reinforcement learning architecture with a Bi-axial LSTM trained with a pseudo-kernel and DQN for exploration and coherence.
result The model generates polyphonic music that performs well quantitatively and qualitatively.
New system for automatic music emotion recognition considers multiple emotions simultaneously.
problem Automatic recognition of simultaneous and multiplicity of emotions in music.
method Comparison of multilabel and multiclass machine learning algorithms on the Emotify dataset.
result The Geneva Emotional Music Scale 9 is adopted for multilabel and multiclass classification of music emotions.
MuLan links music audio to natural language tags.
problem Traditional music tagging systems use rigid attributes; MuLan aims to link audio directly to natural language.
method Joint audio-text embedding model trained on 44 million music recordings and text annotations.
result MuLan's embeddings enable zero-shot functionalities and transfer learning.
Model generates music to connect missing parts, leveraging latent space of VAE.
problem Music inpainting from missing or lost information.
method Deep learning model using VAE latent space and RNN to traverse latent space conditioned on past and future musical contexts.
result Model generates meaningful music inpaintings, connecting musical excerpts.
BachProp generates music in various styles using deep learning.
problem Creating music algorithms that can adapt to multiple styles.
method Developed a novel music representation and trained a deep network to predict note transitions.
result BachProp generates music scores that better capture features of original corpora.
Trains word embeddings from music and text data to link music contexts.
problem Varying vocabulary size and musical relevance in word embeddings.
method Combines general text and music-specific data to train word embeddings.
result Trained embeddings better associate music contexts with compositions.
Music SketchNet generates missing measures in incomplete music pieces, guided by user input.
problem Generating missing measures in incomplete monophonic musical pieces.
method Introducing SketchVAE for factorized representation of rhythm and pitch, and two discriminative architectures for guided music completion.
result Our approach outperforms state-of-the-art models in both objective and subjective evaluations.
System composes polyphonic music using LSTM and RL.
problem Complex polyphonic music composition.
method Divided music into monophonic streams, trained LSTM to generate sequences, used RL to find pleasant compositions.
result System generates intricate melodies, chords, and contrapuntal sequences.
The study uses music chords to predict Brazilian music genres.
problem Classifying popular Brazilian music genres based on harmonic structures.
method Extracted and engineered harmonically related features from chords data, used random forest model for classification.
result Features from harmonic elements can predict Brazilian music genres.
We propose a novel approach for the generation of polyphonic music based on LSTMs. We generate music in two steps. First, a chord LSTM predicts a chord progression based on a chord embedding. A second LSTM then generates polyphonic music from the predicted chord progression. The generated music sounds pleasing and harm…
Word2Vec captures musical relationships in complex polyphonic music.
problem Capturing meaningful relationships in musical contexts.
method Skip-gram version of word2vec applied to music slices from a large corpus.
result Word2Vec embeddings reveal functional chord and harmonic associations.
Recently, digital music libraries have been developed and can be plainly accessed. Latest research showed that current organization and retrieval of music tracks based on album information are inefficient. Moreover, they demonstrated that people use emotion tags for music tracks in order to search and retrieve them. In…
Adversarial autoencoder improves music latent space learning.
problem Learning effective latent spaces for symbolic music data.
method Adversarial regularization with Gaussian mixtures.
result MusAE outperforms standard VAEs in reconstruction and interpolation.
Music generation research has grown in popularity over the past decade, thanks to the deep learning revolution that has redefined the landscape of artificial intelligence. In this paper, we propose a novel approach to music generation inspired by musical segment concatenation methods and hash learning algorithms. Given…
Bi-LSTM with attention generates jazz music with rich nuances.
problem Challenges in producing realistic music with structure and rationality.
method Deep learning, Bi-directional Long Short Term Memory (Bi-LSTM) Neural Network with Attention.
result Bi-LSTMs with attention preserve the richness and technical nuances of old style music.
Paper introduces a new model for polyphonic music composition.
problem Creating music with multiple interwoven voices.
method Developed a coupled recurrent model using probabilistic factorization and neural network ideas.
result Trained models for single-voice and multi-voice composition on a large dataset.
Generative model creates realistic dance poses from music.
problem Generating human-like dance poses from music.
method Music feature encoder, pose generator, music genre classifier integrated.
result Generative autoregressive model synthesizes dance sequences up to 5,000 frames.
Generating music medleys is about finding an optimal permutation of a given set of music clips. Toward this goal, we propose a self-supervised learning task, called the music puzzle game, to train neural network models to learn the sequential patterns in music. In essence, such a game requires machines to correctly sor…
This research improves neural synthesizers for music sounds from speech data.
problem Applying speech synthesis techniques to musical instrument sounds.
method Comparison of three neural synthesizers in three scenarios: training, zero-shot learning, and fine-tuning.
result Neural synthesizers trained on speech data and fine-tuned on music data perform better.
Anticipatory model generates music with control over events.
problem Controlling symbolic music generation.
method Interleaving event and control sequences to predict future events.
result Anticipatory model matches autoregressive models in performance and can infill control tasks.
The paper models musical motif transformations in Beethoven's works.
problem Understanding how motifs transform in symbolic music.
method Developed a probabilistic framework using Conditional Random Fields.
result Identified patterns of motif transformations and their co-occurrences.
EC^2-VAE generates music analogies by disentangling pitch and rhythm representations.
problem Disentangling music representations for generating creative analogies.
method Explicitly-constrained variational autoencoder (EC^2-VAE) for disentangling pitch and rhythm representations.
result EC^2-VAE enables the generation of music analogies by borrowing representations from different pieces.
We consider the task of multimodal music mood prediction based on the audio signal and the lyrics of a track. We reproduce the implementation of traditional feature engineering based approaches and propose a new model based on deep learning. We compare the performance of both approaches on a database containing 18,000 …
Paper compares XGB and BPNN for music style classification.
problem Efficient music style classification using different methods.
method Feature extraction for timbral texture, rhythmic content, and pitch content; comparative evaluation of XGB and BPNN.
result XGB outperforms BPNN for small datasets in music classification.
New dataset and models generate piano music with coherent structure across multiple timescales.
problem Generating coherent musical structure with neural networks is challenging.
method Used notes as an intermediate representation to model and synthesize music across multiple timescales.
result Trained models capable of transcribing, composing, and synthesizing audio waveforms with coherent musical structure.
The study assesses music as an investment asset class using discounted cashflow models.
problem Quantifying the risk and return characteristics of music royalty assets.
method Fitting three discounted cashflow models to Royalty Exchange platform transactions and backtesting performance.
result Life of Rights music assets had risk and return characteristics comparable to stocks in the S\&P500 over 5 years.
Study develops supervised algorithm for symbolic music style translation.
problem Transforming musical style while maintaining original content.
method Synthetic data generation for aligned training data, encoder-decoder model.
result Trained models produce meaningful accompaniments for real MIDI recordings.
Realistic music generation is a challenging task. When building generative models of music that are learnt from data, typically high-level representations such as scores or MIDI are used that abstract away the idiosyncrasies of a particular performance. But these nuances are very important for our perception of musical…
Paper proposes LSTM for automatic music generation.
problem Generating music without human intervention.
method Recurrent Neural Networks (RNN), specifically LSTM.
result Model generates new melodies with high accuracy.
FIGARO generates symbolic music with fine-grained control.
problem Minimal control over generated music sequences.
method Description-to-sequence task, learning conditional distribution of sequences given high-level descriptions.
result State-of-the-art controllable symbolic music generation.
A new neural network separates vocals from music accompaniment.
problem Separating vocals from music accompaniment in recordings.
method Self-attention convolutional neural network (CNN) with densely-connected blocks.
result 19.5% relative improvement in vocals separation.
Real music signals are highly variable, yet they have strong statistical structure. Prior information about the underlying physical mechanisms by which sounds are generated and rules by which complex sound structure is constructed (notes, chords, a complete musical score), can be naturally unified using Bayesian modell…
Deep generative models such as Variational Autoencoders (VAEs) and Generative Adversarial Networks (GANs) have recently been applied to style and domain transfer for images, and in the case of VAEs, music. GAN-based models employing several generators and some form of cycle consistency loss have been among the most suc…
We present a method for translating music across musical instruments, genres, and styles. This method is based on a multi-domain wavenet autoencoder, with a shared encoder and a disentangled latent space that is trained end-to-end on waveforms. Employing a diverse training dataset and large net capacity, the domain-ind…
A musical instrument based on moduli spaces lets users hear geometric concepts.
problem Understanding geometric structures through auditory means.
method Developed a plastic hormonica based on Farey tessellations and Poincaré disk decorations.
result Users can audibly experience paths in Riemann moduli spaces and listen to mapping classes.
Graph neural networks improve music genre classification on audio datasets.
problem Difficulty in applying deep learning on spectrograms due to lack of quality data and augmentation.
method Combination of CNN and Graph Neural Networks (GNN) with Siamese Neural Networks.
result Achieved state-of-the-art results on GTZAN and AudioSet datasets.
Generating music has a few notable differences from generating images and videos. First, music is an art of time, necessitating a temporal model. Second, music is usually composed of multiple instruments/tracks with their own temporal dynamics, but collectively they unfold over time interdependently. Lastly, musical no…
Aug-Gen improves music generation by augmenting training data with model-produced examples.
problem Lack of high-quality training data for specific musical styles.
method Dataset augmentation using generated examples during training.
result Aug-Gen improves both training duration and quality of generated music.