Filters








4 Hits in 4.2 sec

Music SketchNet: Controllable Music Generation via Factorized Representations of Pitch and Rhythm [article]

Ke Chen, Cheng-i Wang, Taylor Berg-Kirkpatrick, Shlomo Dubnov
2020 arXiv   pre-print
First, we introduce SketchVAE, a novel variational autoencoder that explicitly factorizes rhythm and pitch contour to form the basis of our proposed model.  ...  We focus on generating the missing measures in incomplete monophonic musical pieces, conditioned on surrounding context, and optionally guided by user-specified pitch and rhythm snippets.  ...  Attribution: Ke Chen, Chengi Wang, Taylor Berg-Kirkpatrick, Shlomo Dubnov, "Music SketchNet: Controllable Music Generation via Factorized Representations of Pitch and Rhythm", in Proc. of the 21st Int.  ... 
arXiv:2008.01291v1 fatcat:5ckmumeaunay7dw4raxoi5zcsa

Music SketchNet: Controllable music generation via factorized representations of pitch and rhythm

Ke Chen, Cheng-I Wang, Taylor Berg-Kirkpatrick, Shlomo Dubnov
2020 Zenodo  
First, we introduce SketchVAE, a novel variational autoencoder that explicitly factorizes rhythm and pitch contour to form the basis of our proposed model.  ...  We focus on generating the missing measures in incomplete monophonic musical pieces, conditioned on surrounding context, and optionally guided by user-specified pitch and rhythm snippets.  ...  Attribution: Ke Chen, Chengi Wang, Taylor Berg-Kirkpatrick, Shlomo Dubnov, "Music SketchNet: Controllable Music Generation via Factorized Representations of Pitch and Rhythm", in Proc. of the 21st Int.  ... 
doi:10.5281/zenodo.4245372 fatcat:iacmejik6vcpzepazvgez2u2eq

A Comprehensive Survey on Deep Music Generation: Multi-level Representations, Algorithms, Evaluations, and Future Directions [article]

Shulei Ji, Jing Luo, Xinyu Yang
2020 arXiv   pre-print
levels of music generation: score generation produces scores, performance generation adds performance characteristics to the scores, and audio generation converts scores with performance characteristics  ...  However, the development history, the model evolution, as well as the pros and cons of same music generation task have not been clearly illustrated.  ...  [29] used RNNs to generate monophonic music note by note via predicting note pitches and durations.  ... 
arXiv:2011.06801v1 fatcat:cixou3d2jzertlcpb7kb5x5ery

Chord-Conditioned Melody Choralization with Controllable Harmonicity and Polyphonicity [article]

Shangda Wu, Xiaobing Li, Maosong Sun
2022 arXiv   pre-print
Experimental results reveal the effectiveness of our data representation and the controllability of DeepChoir over harmonicity and polyphonicity.  ...  To enable neural networks to learn the general principles of counterpoint from Bach's chorales, we first design a music representation that encoded chord symbols for chord conditioning.  ...  Chen et al. present Music SketchNet [3] , a new framework to explore decoupling latent variables in music generation.  ... 
arXiv:2202.08423v2 fatcat:5y3wjybm65dohly3uuypw6yi3u