SOTAVerified

Music Modeling

( Image credit: R-Transformer )

Papers

Recently AddedMost HypedMost ActiveNeeds VerificationMost Verified

Showing 1–34 of 34 papers

TitleStatusHype
Frechet Music Distance: A Metric For Generative Symbolic Music EvaluationCode1
A Domain-Knowledge-Inspired Music Embedding Space and a Novel Attention Mechanism for Symbolic Music ModelingCode1
Rethinking Neural Operations for Diverse TasksCode1
Pop Music Transformer: Beat-based Modeling and Generation of Expressive Pop Piano CompositionsCode1
Learning Style-Aware Symbolic Music Representations by Adversarial AutoencodersCode1
Enabling Factorized Piano Music Modeling and Generation with the MAESTRO DatasetCode1
Music TransformerCode1
An Empirical Evaluation of Generic Convolutional and Recurrent Networks for Sequence ModelingCode1
Empirical Evaluation of Gated Recurrent Neural Networks on Sequence ModelingCode1
SLEEPING-DISCO 9M: A large-scale pre-training dataset for generative music modeling—0
MuPT: A Generative Symbolic Music Pretrained Transformer—0
Impact of time and note duration tokenizations on deep learning symbolic music modelingCode0
Low-Rank Constraints for Fast Inference in Structured ModelsCode0
Gates Are Not What You Need in RNNsCode0
MuSLCAT: Multi-Scale Multi-Level Convolutional Attention Transformer for Discriminative Music Modeling on Raw Waveforms—0
Recurrently Controlling a Recurrent Network with Recurrent Networks Controlled by More Recurrent Networks—0
PopMAG: Pop Music Accompaniment Generation—0
Metagross: Meta Gated Recursive Controller Units for Sequence Modeling—0
Improving Polyphonic Music Models with Feature-Rich EncodingCode0
Gating Revisited: Deep Multi-layer RNNs That Can Be TrainedCode0
Seq-U-Net: A One-Dimensional Causal U-Net for Efficient Sequence ModellingCode0
R-Transformer: Recurrent Neural Network Enhanced TransformerCode0
Bivariate Beta-LSTMCode0
Counterpoint by ConvolutionCode0
Tensor Variable Elimination for Plated Factor Graphs—0
Preventing Gradient Explosions in Gated Recurrent Units—0
Learning a Predictive Model for Music Using PULSE—0
Recurrent Ladder Networks—0
Diagonal RNNs in Symbolic Music ModelingCode0
Deep Learning for MusicCode0
Sequential Neural Models with Stochastic LayersCode0
LSTM: A Search Space OdysseyCode0
10,000+ Times Accelerated Robust Subset Selection (ARSS)—0
Modeling Temporal Dependencies in High-Dimensional Sequences: Application to Polyphonic Music Generation and TranscriptionCode0
Show:102550
All datasetsJSB ChoralesNottingham

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1GRUNLL8.54—Unverified
2Seq-U-NetNLL8.17—Unverified
3TCNNLL8.15—Unverified
4TCNNLL8.1—Unverified
5RNN-RBMNLL6.27—Unverified
6RNN-NADENLL5.56—Unverified
7CoCoNetNLL2.22—Unverified
8Music TransformerNLL0.34—Unverified
9TonicNetNLL0.22—Unverified
10TonicNetNLL0.21—Unverified
#ModelMetricClaimedVerifiedStatus
1RNNNLL4.05—Unverified
2GRUNLL3.46—Unverified
3TransformerNLL3.34—Unverified
4LSTMNLL3.29—Unverified
5TCNNLL3.07—Unverified
6Seq-U-NetNLL2.97—Unverified
7TCNNLL2.78—Unverified
8R-TransformerNLL2.37—Unverified