Papers with Code 아카이브
Music Modeling
태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.
- 하위 태스크
- 0
- 평가표
- 2
- 보존된 평가 기록
- 18
<span style="color:grey; opacity: 0.6">( Image credit: R-Transformer )</span>
논문
이 태스크와 하위 분야의 관련 논문입니다. 실제 성능 비교는 평가 결과에서 확인하세요.
Frechet Music Distance: A Metric For Generative Symbolic Music Evaluation
MuPT: A Generative Symbolic Music Pretrained Transformer
Impact of time and note duration tokenizations on deep learning symbolic music modeling
A Domain-Knowledge-Inspired Music Embedding Space and a Novel Attention Mechanism for Symbolic Music Modeling
Low-Rank Constraints for Fast Inference in Structured Models
Gates Are Not What You Need in RNNs
MuSLCAT: Multi-Scale Multi-Level Convolutional Attention Transformer for Discriminative Music Modeling on Raw Waveforms
Rethinking Neural Operations for Diverse Tasks
PopMAG: Pop Music Accompaniment Generation
Pop Music Transformer: Beat-based Modeling and Generation of Expressive Pop Piano Compositions
Learning Style-Aware Symbolic Music Representations by Adversarial Autoencoders
Improving Polyphonic Music Models with Feature-Rich Encoding
Gating Revisited: Deep Multi-layer RNNs That Can Be Trained
Seq-U-Net: A One-Dimensional Causal U-Net for Efficient Sequence Modelling
R-Transformer: Recurrent Neural Network Enhanced Transformer
Bivariate Beta-LSTM
Counterpoint by Convolution
Tensor Variable Elimination for Plated Factor Graphs
Enabling Factorized Piano Music Modeling and Generation with the MAESTRO Dataset
Music Transformer
An Empirical Evaluation of Generic Convolutional and Recurrent Networks for Sequence Modeling
Learning a Predictive Model for Music Using PULSE
Recurrent Ladder Networks
Diagonal RNNs in Symbolic Music Modeling
Deep Learning for Music
Sequential Neural Models with Stochastic Layers
LSTM: A Search Space Odyssey
Empirical Evaluation of Gated Recurrent Neural Networks on Sequence Modeling
10,000+ Times Accelerated Robust Subset Selection (ARSS)
Modeling Temporal Dependencies in High-Dimensional Sequences: Application to Polyphonic Music Generation and Transcription
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.