Filters








9 Hits in 2.7 sec

dMelodies: A music dataset for disentanglement learning

Ashis Pati, Siddharth Kumar Gururani, Alexander Lerch
2020 Zenodo  
The dataset is large enough (? 1.3 million data points) to train and test deep networks for disentanglement learning.  ...  This will also provide a means for evaluating algorithms specifically designed for music.  ...  Attribution: Ashis Pati, Siddharth Gururani, Alexander Lerch, "dMelodies: A Music Dataset for Disentanglement Learning", in Proc. of the 21st Int.  ... 
doi:10.5281/zenodo.4245381 fatcat:rtvn5zwkjbevxnldnhlxo7l4he

dMelodies: A Music Dataset for Disentanglement Learning [article]

Ashis Pati, Siddharth Gururani, Alexander Lerch
2020 arXiv   pre-print
This will also provide a means for evaluating algorithms specifically designed for music.  ...  The dataset is large enough (approx. 1.3 million data points) to train and test deep networks for disentanglement learning.  ...  ACKNOWLEDGMENT The authors would like to thank Nvidia Corporation for their donation of a Titan V awarded as part of the GPU (Graphics Processing Unit) grant program which was used for running several  ... 
arXiv:2007.15067v1 fatcat:47kpogb5lnempp5rtyx5xarmcu

Is Disentanglement enough? On Latent Representations for Controllable Music Generation [article]

Ashis Pati, Alexander Lerch
2021 arXiv   pre-print
In this paper, we focus on the relationship between disentanglement and controllability by conducting a systematic study using different supervised disentanglement learning algorithms based on the Variational  ...  Improving controllability or the ability to manipulate one or more attributes of the generated data has become a topic of interest in the context of deep generative models of music.  ...  ACKNOWLEDGMENTS The authors would like to thank NVIDIA Corporation (Santa Clara, CA, United States) for supporting this research via the NVIDIA GPU Grant program.  ... 
arXiv:2108.01450v1 fatcat:ax64vd5girdfdbrue27xh2mxa4

Is Disentanglement enough? On Latent Representations for Controllable Music Generation

Ashis Pati, Alexander Lerch
2021 Zenodo  
In this paper, we focus on the relationship between disentanglement and controllability by conducting a systematic study using different supervised disentanglement learning algorithms based on the Variational  ...  Improving controllability or the ability to manipulate one or more attributes of the generated data has become a topic of interest in the context of deep generative models of music.  ...  learning methods for musical data.  ... 
doi:10.5281/zenodo.5624590 fatcat:ibnbm5w5pbduroz6gbfn2rlate

Towards Robust Unsupervised Disentanglement of Sequential Data – A Case Study Using Music Audio [article]

Yin-Jyun Luo, Sebastian Ewert, Simon Dixon
2022 arXiv   pre-print
We conduct quantitative and qualitative evaluations to demonstrate its robustness in terms of disentanglement on both artificial and real-world music audio datasets.  ...  As a countermeasure, we propose TS-DSAE, a two-stage training framework that first learns sequence-level prior distributions, which are subsequently employed to regularise the model and facilitate auxiliary  ...  Acknowledgments The first author is a research student at the UKRI CDT in AI and Music, supported by Spotify.  ... 
arXiv:2205.05871v2 fatcat:forvy37y4zeb7octza4kh36gtu

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
The utilization of deep learning techniques in generating various contents (such as image, text, etc.) has become a trend.  ...  In addition, we summarize the datasets suitable for diverse tasks, discuss the music representations, the evaluation methods as well as the challenges under different levels, and finally point out several  ...  Others 1) dMELODIES for Disentanglement Learning There is no standard dataset in music for disentanglement learning, so it is impossible to compare different disentanglement methods and technologies  ... 
arXiv:2011.06801v1 fatcat:cixou3d2jzertlcpb7kb5x5ery

MeloForm: Generating Melody with Musical Form based on Expert Systems and Neural Networks [article]

Peiling Lu, Xu Tan, Botao Yu, Tao Qin, Sheng Zhao, Tie-Yan Liu
2022 arXiv   pre-print
However, for neural network-based music generation, it is difficult to do so due to the lack of labelled data on musical form.  ...  MeloForm enjoys the advantages of precise musical form control by expert systems and musical richness learning via neural models.  ...  designed latent factors to create 2-bar melodies for improving data diversity in disentanglement learning.  ... 
arXiv:2208.14345v1 fatcat:fs7velipdne5nidhukjhusyzhe

Controllable Data Generation by Deep Learning: A Review [article]

Shiyu Wang, Yuanqi Du, Xiaojie Guo, Bo Pan, Liang Zhao
2022 arXiv   pre-print
Recently, the advancement of deep learning induces expressive methods that can learn the underlying representation and properties of data.  ...  This article provides a systematic review of this promising research area, commonly known as controllable deep data generation.  ...  combination of nine latent factors that span ordinal, categorical, and binary types, was originally intended for disentanglement learning on music generation [320] . dMelodies was specifically used for  ... 
arXiv:2207.09542v3 fatcat:porb76v7hzadfcdxvfwygut7h4

Game Redesign in No-regret Game Playing

Yuzhe Ma, Young Wu, Xiaojin Zhu
2022 Proceedings of the Thirty-First International Joint Conference on Artificial Intelligence   unpublished
We study the game redesign problem in which an external designer has the ability to change the payoff function in each round, but incurs a design cost for deviating from the original game.  ...  The players apply no-regret learning algorithms to repeatedly play the changed games with limited feedback.  ...  Acknowledgments The first author is a research student at the UKRI CDT in AI and Music, supported by Spotify.  ... 
doi:10.24963/ijcai.2022/458 fatcat:dcdbyc2m75d5hoidd6twp44cdi