Filters








6,846 Hits in 5.9 sec

A Directable Performance Rendering System : Itopul

Mitsuyo Hashida, Yosuke Ito, Haruhiro Katayose
2008 Zenodo  
One of the advantages of case-based systems is that theycan generate expressions even if the user doesn't know howthe system applies expression rules.  ...  After discussing the functions requiredfor user-oriented interface for performance rendering systems, this paper proposes a directable case-based performance rendering system, called Itopul.  ...  Meanwhile, one of the advantages of case-based systems is that they can generate expressions even if the user doesn't know how the system applies expression rules.  ... 
doi:10.5281/zenodo.1179558 fatcat:wbtzctrbkncjzatf6eyfkczi3u

Generative Melody Composition with Human-in-the-Loop Bayesian Optimization

Yijun Zhou, Yuki Koyama, Masataka Goto, Takeo Igarashi
2020 Zenodo  
This process is iteratively performed based on BO techniques until the user finds the desired melody. We conducted a pilot study using our prototype system, suggesting the potential of this approach.  ...  This system takes a mixed-initiative approach; the system generates candidate melodies to evaluate, and the user evaluates them and provides preferential feedback (i.e., picking the best melody among the  ...  The generation of candidate melodies by the system is based on BO, which tries to make the query to the user as effective in terms of the number of necessary iterations as possible.  ... 
doi:10.5281/zenodo.4285363 fatcat:wwpy75aolrfuvkf45wjjakfmxi

Generative Melody Composition with Human-in-the-Loop Bayesian Optimization [article]

Yijun Zhou, Yuki Koyama, Masataka Goto, Takeo Igarashi
2020 arXiv   pre-print
This process is iteratively performed based on BO techniques until the user finds the desired melody. We conducted a pilot study using our prototype system, suggesting the potential of this approach.  ...  This system takes a mixed-initiative approach; the system generates candidate melodies to evaluate, and the user evaluates them and provides preferential feedback (i.e., picking the best melody among the  ...  The generation of candidate melodies by the system is based on BO, which tries to make the query to the user as effective in terms of the number of necessary iterations as possible.  ... 
arXiv:2010.03190v1 fatcat:3mjh476ldreytbea7zruzgz74y

Sensoring a Generative System to Create User-Controlled Melodies

María Navarro-Cáceres, Wataru Hashimoto, Sara Rodríguez-González, Belén Pérez-Lancho, Juan Manuel Corchado
2018 Sensors  
The system is based on a Case-Based Reasoning (CBR) architecture, enabling it to learn from previous compositions and to improve its performance over time.  ...  Most of them also believed that the partial control of the device was essential for the quality of the generated music.  ...  Conflicts of Interest: The authors declare no conflict of interest.  ... 
doi:10.3390/s18103201 pmid:30248966 pmcid:PMC6210176 fatcat:h5l7qyuvebci5pk27xpb2rb3ny

Description-Based Design of Melodies

François Pachet
2009 Computer Music Journal  
The choice of the feature set will influence the capacity of the system to faithfully learn user tags, but identifying a reasonable feature set is usually straightforward.  ...  Another application of this paradigm is to use the system to control the generation of jazz improvisations as an extension of the Continuator system (Pachet 2004) .  ... 
doi:10.1162/comj.2009.33.4.56 fatcat:shd2dubqanh4ba2gho5zdphfbe

Melodic Outline Extraction Method For Non-Note-Level Melody Editing

Yuichi Tsuchiya, Tetsuro Kitahara
2013 Proceedings of the SMC Conferences  
Masaki Matsubara (University of Tsukuba) for their valuable comments.  ...  As a target of editing, we used a four-measure melody generated by Orpheus [9] , which generates a melody based on the prosody of Japanese lyrics.  ...  AND EXPERIMENTS Implementation We implemented a system for melody editing based on the proposed method.  ... 
doi:10.5281/zenodo.850304 fatcat:hlokps4gy5f4xitayn5ucb2yjq

Fuguegenerator - Collaborative Melody Composition Based On A Generative Approach For Conveying Emotion In Music

Niklas Klügel, Gerhard Hagerer, Georg Groh
2014 Proceedings of the SMC Conferences  
Acknowledgments We are grateful to Isaac Wallis for sharing his source code to base our prototypical implementation on.  ...  Our generative approach is rule based inasmuch as it applies transformations that we have formulated beforehand to modify the users' input (cp. [9, p. 236-244] for a review of related systems).  ...  Furthermore, controls for valence and arousal are both part of the shared and private workspace of the respective user: valence is a global (shared) control and arousal is a private control for each user  ... 
doi:10.5281/zenodo.850763 fatcat:l56lmmqovfgejbg2igx4xs6nxa

Expansion on Description-Based Design of Melodies

Avneesh Sarwate, Rebecca Fiebrink
2013 Zenodo  
We also present a user study in which users had some success in transforming melodies and describe the implications of these results for future work.  ...  This work-in-progress paper describes attempted improvements on Pachet's Description-Based Design (DBD), a system that uses machine learning to generate melodies.  ...  Based on the results of the evaluation, it seems reasonable to conclude that the quality of randomly generated melodies far outweighs the interface as the bottleneck for satisfactory training.  ... 
doi:10.5281/zenodo.4285544 fatcat:wwezmugsljcn5j4idbyw2imv7m

Interfaces for Improvising with a Jazz Melody Generation System

Joe Munday, Ángel Faraldo, Perfecto Herrera
2017 Zenodo  
Focussing on jazz melodies specifically, two prospective interfaces were developed that allow a performer interact and direct the melody generation in collaboration with the system, allowing for live performance  ...  Both computational and human evaluation of the melodic output of the system are proposed, along with user testing in order to review both the musical and performance aspects of the system.  ...  so the user is forced to put a level of trust in the system and the output of the melody generation, and give up an element of control.  ... 
doi:10.5281/zenodo.3770120 fatcat:okxtvyzhfvd2hez4j56nyoweba

Music Interfaces For Novice Users : Composing Music On A Public Display With Hand Gestures

Gilbert Beyer, Max Meier
2011 Zenodo  
Our software solution enables users to control melodies by the interaction, utilizing a novel technique of algorithmic composition based on soft constraints.  ...  We present a system that allows users to create harmonic melodies without being in need of a previous training period.  ...  For example, music can be generated in such a way that it resembles the melody of a wellknown song.  ... 
doi:10.5281/zenodo.1177963 fatcat:ibsbw7sqkzb2lesrepgmrwaccu

BayesianBand: Jam Session System Based on Mutual Prediction by User and System [chapter]

Tetsuro Kitahara, Naoyuki Totani, Ryosuke Tokuami, Haruhiro Katayose
2009 Lecture Notes in Computer Science  
To build this system, we constructed a model for melody prediction and chord inference based on a Bayesian network.  ...  The user, while improvising, is also expected to predict the chord progression generated by the system; accordingly, a cooperative jam session based on the mutual prediction will be achieved.  ...  In general, Bayesian networks should be singly connected because when this is the case, a low-complexity algorithm for probability calculation can be applied.  ... 
doi:10.1007/978-3-642-04052-8_17 fatcat:didn4fkp5rfyhkqv72yfsfyqi4

Melody oriented interactive chaotic sound generation system using music conductor gesture

Shuai Chen, Yoichiro Maeda, Yasutake Takahashi
2014 2014 IEEE International Conference on Fuzzy Systems (FUZZ-IEEE)  
In the research of interactive music generation, we propose a music generation method, that the computer  ...  Since it is difficult for our system to generate main melody automatically, we make the melody specifiable by our system users.  ...  There are already existing interactive systems controlling music or sound based on human body movements, for example, Sound Sculpting[1].  ... 
doi:10.1109/fuzz-ieee.2014.6891811 dblp:conf/fuzzIEEE/ChenMT14 fatcat:rrtzfuisuvbhvoep44hmse6wuy

Controlling interactive evolution of 8-bit melodies with genetic programming

Maximos A. Kaliakatsos-Papakostas, Michael G. Epitropakis, Andreas Floros, Michael N. Vrahatis
2012 Soft Computing - A Fusion of Foundations, Methodologies and Applications  
A modification of the GP operators is proposed that allows the user to have control on the randomness of the evolutionary process.  ...  For the automatic creation of art and especially for music synthesis, user fatigue requires that the evolutionary process produces interesting content that evolves fast.  ...  Acknowledgments The authors would like to thank the anonymous reviewers for their valuable comments and ideas that helped to improve and extend the content as well as the clarity of this paper.  ... 
doi:10.1007/s00500-012-0872-y fatcat:5knxs4a5vbbaddnnfnltknpy5y

Music Generation System Based on a Human Instinctive Creativity

Hidefumi Ohmura, Takuro Shibayama, Keiji Hirata, Satoshi Tojo
2018 Zenodo  
We focused on the creativity of creating simple melodies such as humming, and developed a system that generated three melodies based on the physical relationship of notes and probability density functions  ...  Moreover, we con(cid:12)rmed that the output melodies of the system included various musical elements such as mode, scale, and rhythm.  ...  The system outputs up to three melody lines. Users control parameters of the probability density functions for pitches and rhythm.  ... 
doi:10.5281/zenodo.4285474 fatcat:ughl3ftd3fgyjctocgt5dptiru

The EyeHarp: A Gaze-Controlled Musical Instrument

Zacharias Vamvakousis, Rafael Ramírez
2011 Zenodo  
The user can play music in real time controlling the chords and melody of his composition through an intuitive interface based on the pie menus.  ...  The instrument can also be controlled using any input device that can take control of the mouse pointer, and thus it could be appropriate for many cases of people with disabilities.  ...  In the system, the coordinates of the user' s gaze are sent to MAX/MSP for generating sound.  ... 
doi:10.5281/zenodo.3754027 fatcat:wor6ycnrunbqjjgm3zefwf7iea
« Previous Showing results 1 — 15 out of 6,846 results