Music Modeling On Jsb Chorales
Metriken
NLL
Parameters
Ergebnisse
Leistungsergebnisse verschiedener Modelle zu diesem Benchmark
Modellname | NLL | Parameters | Paper Title | Repository |
|---|---|---|---|---|
| TCN | 8.154 | 534K | Seq-U-Net: A One-Dimensional Causal U-Net for Efficient Sequence Modelling | - |
| TonicNet | 0.220 | - | Improving Polyphonic Music Models with Feature-Rich Encoding | - |
| Music Transformer | 0.335 | - | Music Transformer | - |
| CoCoNet | 2.22 | - | Counterpoint by Convolution | - |
| RNN-NADE | 5.56 | - | Modeling Temporal Dependencies in High-Dimensional Sequences: Application to Polyphonic Music Generation and Transcription | - |
| RNN-RBM | 6.27 | - | Modeling Temporal Dependencies in High-Dimensional Sequences: Application to Polyphonic Music Generation and Transcription | - |
| TonicNet | 0.208 | - | JS Fake Chorales: a Synthetic Dataset of Polyphonic Music with Human Annotation | |
| Seq-U-Net | 8.173 | 522K | Seq-U-Net: A One-Dimensional Causal U-Net for Efficient Sequence Modelling | - |
| GRU | 8.54 | - | Empirical Evaluation of Gated Recurrent Neural Networks on Sequence Modeling | - |
| TCN | 8.10 | - | An Empirical Evaluation of Generic Convolutional and Recurrent Networks for Sequence Modeling | - |
0 of 10 row(s) selected.