CRNN improves artist classification with temporal audio features.
problem Artist classification using deep learning with temporal structure.
method Convolutional Recurrent Neural Network (CRNN) applied to music artist identification dataset.
result Best model achieves an average F1 score of 0.937.
The automated recognition of music genres from audio information is a challenging problem, as genre labels are subjective and noisy. Artist labels are less subjective and less noisy, while certain artists may relate more strongly to certain genres. At the same time, at prediction time, it is not guaranteed that artist …
We address the problem of disambiguating large scale catalogs through the definition of an unknown artist clustering task. We explore the use of metric learning techniques to learn artist embeddings directly from audio, and using a dedicated homonym artists dataset, we compare our method with a recent approach that lea…
A study compares local music recommendation algorithms, finding neighborhood-based methods perform best.
problem Cold-start problem for local artists with little user preference data.
method Comparison of three recommender system algorithms (IIN, ALS, BPR) on local music recommendation task.
result Neighborhood-based approach (IIN) performs best for local music recommendation.
Paper classifies Brazilian music genres using song lyrics with BLSTM network.
problem Classifying Brazilian music genres from lyrics.
method Used BLSTM network combined with SVM, Random Forest, and word embeddings.
result BLSTM outperforms other models with an F1-score of 0.48.
Paper proposes a new ML framework to enhance creativity in music generation.
problem Current generative models struggle to produce music outside their training dataset.
method Develops a new ML objective to address creativity limitations.
result Proposed framework could improve generative models' creativity.
I find a topological arrangement of assets traded in a phonographic market which has associated a meaningful economic taxonomy. I continue using the Minimal Spanning Tree and the Life-time Of Correlations between assets, but now outside the stock markets. This is the first attempt to use these methods on phonographic m…
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.
Jukebox generates high-fidelity songs with singing in raw audio.
problem Generating music with singing in raw audio.
method Multi-scale VQ-VAE for compression, autoregressive Transformers for modeling.
result Generates high-fidelity and diverse songs with coherence up to multiple minutes.
The paper tackles carousel personalization in music streaming apps using contextual bandits.
problem Selecting relevant items to display in carousels for personalized content recommendation.
method Modeling carousel personalization as a contextual multi-armed bandit problem with multiple plays, cascade-based updates and delayed batch feedback.
result Empirically shows the effectiveness of the framework in capturing characteristics of real-world carousels.
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.
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.
Study finds conformity bias drives music sampling traditions.
problem How frequency-based bias drives cultural diversity in music sampling.
method Agent-based simulations in approximate Bayesian computation framework.
result Sampling patterns at population-level consistent with conformity bias.
A model for hit song prediction can be used in the pop music industry to identify emerging trends and potential artists or songs before they are marketed to the public. While most previous work formulates hit song prediction as a regression or classification problem, we present in this paper a convolutional neural netw…
The artistic style of a painting is a subtle aesthetic judgment used by art historians for grouping and classifying artwork. The recently introduced `neural-style' algorithm substantially succeeds in merging the perceived artistic style of one image or set of images with the perceived content of another. In light of th…
Unified model for audio control and style transfer.
problem Explicit control and style transfer in music generation.
method Diffusion autoencoders for semantic feature extraction, disentanglement using adversarial criterion.
result Model generates audio matching timbre targets with specified structure.
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 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.
Music genre classification is an essential tool for music information retrieval systems and it has been finding critical applications in various media platforms. Two important problems of the automatic music genre classification are feature extraction and classifier design. This paper investigates inter-genre similarit…
SVM classifier outperforms other models in classifying musical instruments from IRMAS data.
problem Musical instrument classification from audio signals.
method Implemented supervised (SVM) and unsupervised (Hierarchical Clustering) learning algorithms.
result SVM classifier achieved 79% accuracy on IRMAS data.
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.
Neural nets classify Thai Lukthung songs from other genres.
problem Classifying Thai Lukthung songs for personalized music recommendations.
method Developed neural networks using lyrics and audio features.
result Combined model yields F1 score of 0.86 for Lukthung classification. This paper proposes a method for instrument classification in polyphonic music using monophonic data.
problem Instrument classification in polyphonic music from monophonic data.
method Data augmentation techniques including overlaying audio segments of the same genre, pitch, and tempo synchronization. Convolutional Neural Networks used for classification.
result An ensemble of VGG-like classifiers trained on non-augmented, pitch-synchronized, tempo-synchronized and genre-similar excerpts achieved above 80% LRAP.
A new learning-to-rank approach ensures fairness for item providers in dynamic ranking systems.
problem Myopically optimizing user utility can be unfair to item providers in two-sided markets.
method A controller that integrates unbiased estimators for fairness and utility, dynamically adapting as more data becomes available.
result Empirically, the algorithm is highly practical and robust, ensuring amortized group fairness.
DeepDrummer generates drum loops with human preferences via active learning.
problem Creating drum loops efficiently with user preferences.
method Active learning with a deep neural network classifier.
result System converges to user preferences after few interactions.
Paper tackles artist style transfer using quadratic potential.
problem Applying a specific artist's style to real-world photographs.
method Adversarial training with quadratic potential divergence and integration of deep learning techniques.
result Demonstrates improved quality of artist stylized images.
A model classifies music genres from MP3 files using metric learning and feature extraction.
problem Classifying music genres from MP3 files efficiently and accurately.
method Metric learning and feature extraction using MFCC and PCA.
result Promising results in classification accuracy compared to baseline algorithms.
SCM-GAN converts any song to sound like a different singer.
problem Converting songs to sound like a different artist.
method Transfer learning and GANs to separate vocals and instruments, then convert and merge.
result SCM-GAN improves song conversion metrics by 35% GV and 13% MS.
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.
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…
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.
Predicting dance hits from 1985-2013 using musical features.
problem Predicting which songs will be dance hits.
method Built a database of dance hit songs with features, used multiple classifiers.
result Best model predicts top 10 dance hits with good accuracy.
This paper explores deep learning in music generation, from history to current techniques.
problem Creating music automatically using deep learning.
method Analysis of historical and recent deep learning music generation systems.
result Deep learning can learn musical styles and generate music samples.
Low-dimensional vectors improve semantic understanding of music and language.
problem Noise in shared semantics due to individual brain biases.
method Jointly model multiple brains to learn low-dimensional vector embeddings.
result These embeddings outperform high-dimensional fMRI data in music and language classification.
Neural network generates music scores directly from polyphonic audio.
problem Transcribing music scores directly from polyphonic audio.
method Convolutional Recurrent Neural Network (CRNN) with CTC loss function.
result Model can learn to transcribe scores directly from audio signals.
Bardo Composer generates tabletop RPG music based on player speech.
problem Creating immersive background music for tabletop RPGs.
method Speech recognition, emotion classification, and music generation using a novel beam search algorithm.
result Generated music pieces can be accurately identified by human subjects as conveying the intended emotion.
A new method clusters qualitative data with mixed variables, improving interpretability.
problem Clustering qualitative data with context and high-dimensional mixed datasets.
method Hierarchical Qualitative Clustering (HQC) using Maximum Mean Discrepancy.
result HQC maintains interpretability of qualitative information and clusters effectively.
Feature learning and deep learning have drawn great attention in recent years as a way of transforming input data into more effective representations using learning algorithms. Such interest has grown in the area of music information retrieval (MIR) as well, particularly in music audio classification tasks such as auto…
New method predicts target genres from source genres, unifying music tag systems.
problem Automatic genre inference fails to handle music genre diversity and subjectivity.
method Knowledge-based, statistical, and hybrid translation models.
result Hybrid translation model is most effective for multilabel classification.
Paper tackles musical version matching at segment level using contrastive learning from weakly-labeled data.
problem Match musical versions at the segment level, not just tracks, with weak annotations.
method Proposes contrastive learning from weakly-labeled audio segments, using a new loss variant.
result Breakthrough performance in segment-level evaluation, outperforming state-of-the-art.
We present a feature engineering pipeline for the construction of musical signal characteristics, to be used for the design of a supervised model for musical genre identification. The key idea is to extend the traditional two-step process of extraction and classification with additive stand-alone phases which are no lo…
Improved cover detection in music datasets with novel triplet loss.
problem Challenging task of automatically detecting covers in audio datasets.
method Convolutional neural network mapping melodic features to embeddings, training to minimize cover distance and maximize non-cover distance.
result New prototypical triplet loss improves accuracy for large datasets and live songs.
Speech, Music and Noise classification/segmentation is an important preprocessing step for audio processing/indexing. To this end, we propose a novel 1D Convolutional Neural Network (CNN) - SwishNet. It is a fast and lightweight architecture that operates on MFCC features which is suitable to be added to the front-end …
Principal component analysis (PCA) is a popular method for projecting data onto uncorrelated components in lower dimension, although the optimal number of components is not specified. Likewise, multiple signal classification (MUSIC) algorithm is a popular PCA-based method for estimating directions of arrival (DOAs) of …
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.
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.
Proposes COALA method for learning audio representations aligned with tags.
problem Lack of annotated data for high-performance audio representation learning.
method Aligns latent representations of audio and tags using a contrastive loss.
result Audio embedding model captures both acoustic and semantic characteristics.