Query-based Deep Improvisation

S Dubnov
arXiv preprint arXiv:1906.09155

Universal adversarial perturbations for speech recognition systems

P Neekhara, S Hussain, P Pandey, S Dubnov, J McAuley, F Koushanfar
arXiv preprint arXiv:1905.03828

Expediting TTS Synthesis with Adversarial Vocoding

P Neekhara, C Donahue, M Puckette, S Dubnov, J McAuley
arXiv preprint arXiv:1904.07944

Semantic Interaction with Human Motion Using Query-Based Recombinant Video Synthesis

V Gokul, GP Balakrishnan, T Dubnov, S Dubnov
2019 IEEE Conference on Multimedia Information Processing and Retrieval …

The effect of explicit structure encoding of deep neural networks for symbolic music generation

K Chen, W Zhang, S Dubnov, G Xia, W Li
2019 International Workshop on Multilayer Music Representation and …

Adversarial Reprogramming of Sequence Classification Neural Networks

P Neekhara, S Hussain, S Dubnov, F Koushanfar
arXiv preprint arXiv:1809.01829 1 2018

Rethinking Recurrent Latent Variable Model for Music Composition

ES Koh, S Dubnov, D Wright
2018 IEEE 20th International Workshop on Multimedia Signal Processing (MMSP … 1 2018

Capturing Musical Structure Using Convolutional Recurrent Latent Variable Model

E Koh, D Wright, S Dubnov

Context-aware hidden Markov models of jazz music with variable Markov oracle

C Wang, S Dubnov
Proceedings of the 5th international workshop on musical metacreation (MUME … 1 2017

Re-Visiting the Music Segmentation Problem with Crowdsourcing.

C Wang, GJ Mysore, S Dubnov
ISMIR, 738-744 2 2017

Novel Method of Nonlinear Symbolic Dynamics for Semantic Analysis of Auditory Scenes

P Mouawad, S Dubnov
2017 IEEE 11th International Conference on Semantic Computing (ICSC), 433-438 2017

An Audience-Responsive Robotic Performance Network

C Zyskowski, M de Oliveira, S Dubnov
2017 IEEE 11th International Conference on Semantic Computing (ICSC), 274-275

Machine improvisation with variable markov oracle: Toward guided and structured improvisation

CI Wang, J Hsu, S Dubnov
Computers in Entertainment (CIE) 14 (3), 4 7 2016

An introduction to musical metacreation

P Pasquier, A Eigenfeldt, O Bown, S Dubnov
Computers in Entertainment (CIE) 14 (2), 2 28 2016

Cross-Cultural Multimedia Computing: Semantic and Aesthetic Modeling

S Dubnov, K Burns, Y Kiyoki
Springer 2016

Automatic construction of interactive machine improvisation scenarios from audio recordings

J Arias, M Desainte-Catherine, S Dubnov
4 2016

Information sensibility as a cultural characteristic: Tuning to sound details for aesthetic experience

S Dubnov, K Burns, Y Kiyoki
Cross-Cultural Multimedia Computing, 43-62

Nonlinear dynamics of human creativity

M Rabinovich, I Tristan, S Dubnov
2014 IEEE International Conference on Systems, Man, and Cybernetics (SMC … 2014

Guided music synthesis with variable markov oracle

C Wang, S Dubnov
Tenth Artificial Intelligence and Interactive Digital Entertainment Conference 31 2014

Interactive projection for aerial dance using depth sensing camera

T Dubnov, Z Seldess, S Dubnov
The Engineering Reality of Virtual Reality 2014 9012, 901202 4 2014

Delegating creativity: Use of musical algorithms in machine listening and composition

S Dubnov, G Surges
Digital Da Vinci, 127-158 4 2014

Feature Selection and Composition using PyOracle

A system is described which uses the Audio Oracle algorithm for music analysis and machine improvisation. Some improvements on previous Factor Oracle-based systems are presented, including automatic model calibration based on measures from Music Information Dynamics, facilities for compositional structuring and automation, and an audio-based query mode which uses the input signal to influence the output of the generative system.

Singing Voice Database: The role of the singing acoustic cues in the perception of broad affect dimensions

From the Proceedings of the 10th International Symposium on Computer Music Multidisciplinary Research, Marseille, France, October 15-18, 2013, an experiment that investigates the role of acoustic correlates of the singing voice in the perception of broad affect dimensions using the two-dimensional model of affect.

DistributeDJ: a mobile group music making toolkit

The activity of technology enhanced group music making can offer intriguing insights into musical interaction, new ideas on performance, and more easily provide non expert musi- cians the opportunity to participate. Collaborative improvisations often have a looser structure then traditionally composed score based music, but in most cases there are still sets of structural frameworks to be followed. DistributeDJ, a group music service, is proposed to aid in the creation and execution of flexible collaborative mobile music performances and attract a broader audience participation. Designed to run through an Internet client, the system provides a communication layer between a central performance server and multiple clients that are used to actively manipulate the contents of delivered audio through participant’s mobile interface.

Expressions: Inter-Professional Culture via Coactive Digital Humanities Platform

This paper explores an integrated inter-professional collaborative model and technology for a break-through digital humanities platform called, “Expressions.’ This platform was co-created by the Center for Research in Entertainment & Learning (CREL) at Calit2, UCSD, in partnership with Visual Exchange Network (VEN), which is an hybrid research and production group for upstream multi-venue media.

Audio Oracle analysis of Musical Information Rate

This paper presents a method for analysis of changes in information contents in music based on an audio representa- tion called Audio Oracle (AO). Using compression properties of AO we estimate the amount of information that passes between the past and the present at every instance in a musical signal. This formulation extends the notion of Information Rate (IR) to individual sequences and allows an optimal estimation of the AO threshold parameter. We show that changes in IR correspond to significant musical structures such as sections in a sonata form. Relation to musical perception and applications for composition and improvisation are discussed in the paper.