Neural model synthesizes music with flexible timbre controls.
problem Creating audio samples with varied timbres from musical scores.
method Recurrent neural network conditioned on learned instrument embedding followed by WaveNet vocoder.
result Learned embedding space captures diverse timbres and enables interpolation for morphing.
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.
Review of deep learning techniques for audio signal processing.
problem Improving audio signal processing using deep learning.
method Analysis of various deep learning models and techniques.
result Advancements in speech, music, and environmental sound processing.
Deep learning models generate music with arbitrary control strategies.
problem Lack of efficient methods for generating music with arbitrary control.
method Deep generative models learn to navigate arbitrary sound spaces.
result Deep learning enables high-quality, arbitrary sound synthesis.
SING generates musical notes from instruments in real-time.
problem Efficiently generating high-quality audio from MIDI data.
method Frame-by-frame waveform generation with a single decoder, using a new loss function.
result SING produces significantly improved audio quality compared to state-of-the-art models, with 32x faster training and 2,500x faster inference.
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.
TimbreTron transfers musical timbre using CQT and WaveNet.
problem Transfer musical timbre while preserving pitch, rhythm, and loudness.
method Apply image domain style transfer to CQT representation, then generate high-quality waveform with WaveNet.
result TimbreTron recognizably transfers timbre while preserving musical content.
Model disentangles timbre and pitch for musical instruments.
problem Learning disentangled representations of musical instrument sounds.
method Gaussian mixture variational autoencoders with two separate encoders for timbre and pitch.
result Model successfully disentangles timbre and pitch, enabling controllable synthesis and transfer.
New method allows real-time audio synthesis using non-causal convolutions.
problem Real-time audio synthesis limitations due to offline model constraints.
method Post-training reconfiguration of non-causal models for real-time buffer-based processing.
result Non-causal streaming models can be transformed from offline-trained models without quality loss.
Transformer adapts to multi-instrumental music generation using NES and Lakh MIDI datasets.
problem Generating multi-instrumental music scores with Transformers.
method Adapted Transformer architecture to multi-instrumental setting, used NES-MDB and Lakh MIDI datasets for pre-training.
result Pre-training with Lakh MIDI dataset improves performance for multi-instrumental music generation.
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.
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.
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.
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.
Paper presents a novel waveform-to-waveform model for music source separation.
problem Isolating individual instruments from mixed music recordings.
method Adapted Conv-Tasnet to waveform domain and developed Demucs with U-Net and bidirectional LSTM.
result Demucs achieves superior performance on music source separation tasks, surpassing existing state-of-the-art.
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.
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. 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.
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.
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.
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…
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.
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.
Generates music with coherent rhythm, chords, and melody using LSTM models.
problem Lack of direction and coherence in generated music by neural networks.
method Two-stage LSTM model: first generates harmonic and rhythmic templates, then melodies conditioned on these.
result Subjective test shows improved musical coherence and coherence compared to baselines.
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.
We present a supervised neural network model for polyphonic piano music transcription. The architecture of the proposed model is analogous to speech recognition systems and comprises an acoustic model and a music language model. The acoustic model is a neural network used for estimating the probabilities of pitches in …
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…
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.
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.
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…
The paper trains a neural network to compose music in a nonlinear, human-like manner.
problem Creating music in a non-chronological, revisiting manner.
method Trained a convolutional neural network with blocked Gibbs sampling to approximate human composition.
result Blocked Gibbs sampling improves sample quality and yields better results than ancestral sampling.
Considering music as a sequence of events with multiple complex dependencies, the Long Short-Term Memory (LSTM) architecture has proven very efficient in learning and reproducing musical styles. However, the generation of rhythms requires additional information regarding musical structure and accompanying instruments. …
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.
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…
We investigate the problem of modeling symbolic sequences of polyphonic music in a completely general piano-roll representation. We introduce a probabilistic model based on distribution estimators conditioned on a recurrent neural network that is able to discover temporal dependencies in high-dimensional sequences. Our…
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.
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.
SED integrates synthesis, execution, and debugging for neural program synthesis.
problem Challenges in synthesizing complex programs that match specifications.
method SED combines synthesis, execution, and debugging to improve neural program generation.
result SED reduces error rates and outperforms standard decoding methods.
Paper improves multi-step chord prediction in jazz music.
problem Chord sequence prediction accuracy is poor in multi-step scenarios.
method Aggregated multi-scale encoder-decoder network architecture.
result Our model outperforms state-of-the-art methods in accuracy and perplexity.
SwishNet improves speech, music, and noise classification and segmentation.
problem Speech, Music, and Noise classification/segmentation for audio processing.
method Proposes a fast and lightweight 1D CNN (SwishNet) for MFCC features, trained with knowledge distillation from ImageNet.
result Achieved high accuracy (>97% clip classification, >93% frame-wise segmentation) on MUSAN corpus.
The variational autoencoder (VAE) is a popular probabilistic generative model. However, one shortcoming of VAEs is that the latent variables cannot be discrete, which makes it difficult to generate data from different modes of a distribution. Here, we propose an extension of the VAE framework that incorporates a classi…
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.
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 paper improves polyphonic music models by extracting salient features.
problem Improving performance of polyphonic music models.
method Training a neural network to predict both chords and notes, including extra features.
result Training a neural network to predict extra features improves model performance.
Speech synthesis from EEG features using RNN.
problem Speech synthesis from EEG data.
method Recurrent Neural Network (RNN) regression model to predict acoustic features from EEG features.
result Feasibility of synthesizing speech directly from EEG features demonstrated.
Generates music with video emotion using deep neural networks.
problem Generating music with video emotion.
method Hybrid deep neural network combining ANFIS and LSTM.
result Low mean absolute errors and similar global features in spectrograms.
Generative model blends query input with latent states for structured improvisation.
problem Generating structured music from latent states of a neural network.
method Used a Variational Autoencoder (VAE) trained on a specific style corpus, and controlled blending with a noisy channel.
result Generated music with longer-term structure that blends query input with network style.
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.