292 Hits in 6.2 sec

Magenta Studio: Augmenting Creativity with Deep Learning in Ableton Live

Adam Roberts, Jesse Engel, Yotam Mann, Jon Gillick, Claire Kayacik, Signe Nørly, Monica Dinculescu, Carey Radebaugh, Curtis Hawthorne, Douglas Eck
2019 Zenodo  
Our suite of plug-ins for Ableton Live, named Magenta Studio, is available for download at along with its open source implementation.  ...  The field of Musical Metacreation (MuMe) has produced impressive results for both autonomous and interactive creativity, recently aided by modern deep learning frameworks.  ...  Magenta Studio is based on work by members of the Google Brain team's Magenta project along with contributors to the Magenta and Magenta.js libraries.  ... 
doi:10.5281/zenodo.4285265 fatcat:yjmxojcx4fbyngmofi3hhai6uu

Designing for a Pluralist and User-Friendly Live Code Language Ecosystem with Sema

Francisco Bernardo, Chris Kiefer, Thor Magnusson
2020 Zenodo  
With live coding, the real-time composition of music and other art becomes a performance art by centering on the language of the composition itself, the code.  ...  We provide an overview and design rationale for the early technical implementation of Sema, including technology stack, architecture, user interface, integration of machine learning, and documentation  ...  present design and development goals for the next design iteration of Sema.  ... 
doi:10.5281/zenodo.3939228 fatcat:yjrulfhbo5eovb5h33zpgwxl2y

A Laptop Ensemble Performance System using Recurrent Neural Networks

Rohan Proctor, Charles Patrick Martin
2020 Proceedings of the International Conference on New Interfaces for Musical Expression  
The final implementation of the system offers performers a mixture of high and low-level controls to influence the shape of sequences of notes output by locally run NN models in real time, also allowing  ...  The popularity of applying machine learning techniques in musical domains has created an inherent availability of freely accessible pre-trained neural network (NN) models ready for use in creative applications  ...  Acknowledgments We wish to thank the ANU Laptop Ensemble for participating in live performances with our system.  ... 
doi:10.5281/zenodo.4813481 fatcat:aqpsbtqulbckbprtwn2zqp2loy

MidiNet: A Convolutional Generative Adversarial Network for Symbolic-domain Music Generation [article]

Li-Chia Yang, Szu-Yu Chou, Yi-Hsuan Yang
2017 arXiv   pre-print
Most existing neural network models for music generation use recurrent neural networks.  ...  We conduct a user study to compare the melody of eight-bar long generated by MidiNet and by Google's MelodyRNN models, each time using the same priming melody.  ...  Ten of them understand basic music theory and have the experience of being an amateur musician, so we considered them as people with musical backgrounds, or professionals for short.  ... 
arXiv:1703.10847v2 fatcat:3s6bkrupqbd6jb2fg3dzhunn7e

Midinet: A Convolutional Generative Adversarial Network For Symbolic-Domain Music Generation

Li-Chia Yang, Szu-Yu Chou, Yi-Hsuan Yang
2017 Zenodo  
Ten of them understand basic music theory and have the experience of being an amateur musician, so we considered them as people with musical backgrounds, or professionals for short.  ...  models, for people (top row) with musical backgrounds and (bottom) without musical backgrounds.  ... 
doi:10.5281/zenodo.1415990 fatcat:rkr4w4m2bvdq5jt4le5z26tdiu

A Functional Taxonomy of Music Generation Systems

Dorien Herremans, Ching-Hua Chuan, Elaine Chew
2017 ACM Computing Surveys  
Digital advances have transformed the face of automatic music generation since its beginnings at the dawn of computing.  ...  We present a functional taxonomy for music generation systems with reference to existing systems. The taxonomy organizes systems according to the purposes for which they were designed.  ...  This could lead to real-life practical applications such as real-time music generation for games, and background music for film and video.  ... 
doi:10.1145/3108242 fatcat:wcp2p3mu4fgndclqrwlcwzkyoa

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
This paper attempts to provide an overview of various composition tasks under different music generation levels, covering most of the currently popular music generation tasks using deep learning.  ...  Previous surveys have explored the network models employed in the field of automatic music generation.  ...  This may promote practical applications in real life, such as real-time music generation of games and automatic generation of background music of movies and videos; more importantly, strengthen the interaction  ... 
arXiv:2011.06801v1 fatcat:cixou3d2jzertlcpb7kb5x5ery

Algorithmic interactive music generation in videogames

Alvaro E. Lopez Duarte
2020 SoundEffects  
Some of them are complemented with rules and are assigned to sections with low emotional requirements, but support for real-time interaction in gameplay situations, although desirable, is rarely found.While  ...  Finally, I propose a compositional tool design based in modular instances of algorithmic music generation, featuring stylistic interactive control in connection with an audio engine rendering system.  ...  possibilities, challenges, limits, and techniques of automatic music composition.  ... 
doi:10.7146/se.v9i1.118245 fatcat:yoqonmlm5ncvdgxb2obg7iejwm

Learning to Groove with Inverse Sequence Transformations [article]

Jon Gillick, Adam Roberts, Jesse Engel, Douglas Eck, David Bamman
2019 arXiv   pre-print
Focusing on the case of drum set players, we create and release a new dataset for this purpose, containing over 13 hours of recordings by professional drummers aligned with fine-grained timing and dynamics  ...  We also explore some of the creative potential of these models, including demonstrating improvements on state-of-the-art methods for Humanization (instantiating a performance from a musical score).  ...  Because almost anyone can tap a rhythm regardless of their level of musical background or training, this input modality may be more accessible than musical notation for those who would like to express  ... 
arXiv:1905.06118v2 fatcat:gdn5hv6zbjb3tf5qp4dy4jn53a

MorpheuS: generating structured music with constrained patterns and tension

Dorien Herremans, Elaine Chew
2017 IEEE Transactions on Affective Computing  
Yet, they still face an important challenge, that of long-term structure, which is key to conveying a sense of musical coherence.  ...  A mathematical model for tonal tension quantifies the tension profile and state-of-the-art pattern detection algorithms extract repeated patterns in a template piece.  ...  Casella and Paiva [52] created MAgentA (not to be confused with Google's music generation project Magenta), an abstract framework for a video game background music generation that aims to create "film-like  ... 
doi:10.1109/taffc.2017.2737984 fatcat:3ewbbbh6r5elvkmtwr2aqn5uga

Music Generation by Deep Learning - Challenges and Directions [article]

Jean-Pierre Briot, François Pachet
2017 arXiv   pre-print
The motivation is in using the capacity of deep learning architectures and training techniques to automatically learn musical styles from arbitrary musical corpora and then to generate samples from the  ...  In addition to traditional tasks such as prediction, classification and translation, deep learning is receiving growing attention as an approach for music generation, as witnessed by recent research groups  ...  Acknowledgements This paper is based on the first half of the "Machine-Learning for Symbolic Music Generation" tutorial given at the 18th International Society for Music Information Retrieval Conference  ... 
arXiv:1712.04371v1 fatcat:23nug7n6qzfbllcjnfs5nerbp4

This time with feeling: learning expressive musical performance

Sageev Oore, Ian Simon, Sander Dieleman, Douglas Eck, Karen Simonyan
2018 Neural computing & applications (Print)  
timing and dynamics.  ...  We consider the significance and qualities of the dataset needed for this.  ...  Acknowledgements We gratefully acknowledge the members of the Magenta team at Google Research for numerous discussions. We thank the reviewers for helpful comments.  ... 
doi:10.1007/s00521-018-3758-9 fatcat:ttyik6g6ubev7oari3dfdkzewy

Machine Learning for Computational Creativity: VST Synthesizer Programming

Christopher Mitcheltree, Hideki Koike
2021 Zenodo  
Learning to create music with an audio production Virtual Studio Technology (VST) synthesizer through sound design and note composition is a time-consuming process, usually obtained through inefficient  ...  After this, an expressive and controllable variational autoencoder for generating MIDI notes that can then be rendered by a synthesizer is built and some of its creative and artistic applications are explored  ...  Acknowledgements List of Acronyms Bibliography Acknowledgments I'd like to thank my advisor Professor Koike, the students and staff at the Koike Lab, everyone at Qosmo, and my friends and family for their  ... 
doi:10.5281/zenodo.6351291 fatcat:tqvuepndzjdnzbf2qv23ryweuq

Deep Learning Techniques for Music Generation – A Survey [article]

Jean-Pierre Briot, Gaëtan Hadjeres, François-David Pachet
2019 arXiv   pre-print
. - For what destination and for what use? To be performed by a human(s) (in the case of a musical score), or by a machine (in the case of an audio file).  ...  This paper is a survey and an analysis of different ways of using deep learning (deep artificial neural networks) to generate musical content.  ...  Composition Types We will see that, from an architectural point of view, various types of composition 88 may be used: • Composition -at least two architectures, of the same type or of different types,  ... 
arXiv:1709.01620v4 fatcat:hma4znleorfpvh62cpupxu4fq4

This Time with Feeling: Learning Expressive Musical Performance [article]

Sageev Oore, Ian Simon, Sander Dieleman, Douglas Eck, Karen Simonyan
2018 arXiv   pre-print
We consider the significance and qualities of the data set needed for this.  ...  timing and dynamics.  ...  We thank members and visitors at Google Brain and specifically the Magenta team for discussions, including Adam Roberts, Anna Huang, Colin Raffel, Curtis Hawthorne, David Ha, David So, Fred Bertch, George  ... 
arXiv:1808.03715v1 fatcat:63wxx5d5h5hftgcwo6vsb43ueq
« Previous Showing results 1 — 15 out of 292 results