Get our free extension to see links to code for papers anywhere online!

Chrome logo Add to Chrome

Firefox logo Add to Firefox
Picture for Shlomo Dubnov

Shlomo Dubnov

Comparison and Analysis of Deep Audio Embeddings for Music Emotion Recognition


Apr 13, 2021
Eunjeong Koh, Shlomo Dubnov

Figure 1 for Comparison and Analysis of Deep Audio Embeddings for Music Emotion Recognition
Figure 2 for Comparison and Analysis of Deep Audio Embeddings for Music Emotion Recognition
Figure 3 for Comparison and Analysis of Deep Audio Embeddings for Music Emotion Recognition
Figure 4 for Comparison and Analysis of Deep Audio Embeddings for Music Emotion Recognition
* AAAI 2021 
 * AAAI Workshop on Affective Content Analysis 2021 Camera Ready Version 
  Access Paper or Ask Questions

Bias-Free FedGAN


Mar 17, 2021
Vaikkunth Mugunthan, Vignesh Gokul, Lalana Kagal, Shlomo Dubnov


  Access Paper or Ask Questions

WaveGuard: Understanding and Mitigating Audio Adversarial Examples


Mar 04, 2021
Shehzeen Hussain, Paarth Neekhara, Shlomo Dubnov, Julian McAuley, Farinaz Koushanfar

Figure 1 for WaveGuard: Understanding and Mitigating Audio Adversarial Examples
Figure 2 for WaveGuard: Understanding and Mitigating Audio Adversarial Examples
Figure 3 for WaveGuard: Understanding and Mitigating Audio Adversarial Examples
Figure 4 for WaveGuard: Understanding and Mitigating Audio Adversarial Examples
* Published as a conference paper at Usenix Security 2021 
  Access Paper or Ask Questions

Cross-modal Adversarial Reprogramming


Feb 15, 2021
Paarth Neekhara, Shehzeen Hussain, Jinglong Du, Shlomo Dubnov, Farinaz Koushanfar, Julian McAuley

Figure 1 for Cross-modal Adversarial Reprogramming
Figure 2 for Cross-modal Adversarial Reprogramming
Figure 3 for Cross-modal Adversarial Reprogramming
Figure 4 for Cross-modal Adversarial Reprogramming
* 12 pages, 3 figures 
  Access Paper or Ask Questions

Deep Music Information Dynamics


Feb 01, 2021
Shlomo Dubnov

Figure 1 for Deep Music Information Dynamics
Figure 2 for Deep Music Information Dynamics
Figure 3 for Deep Music Information Dynamics
Figure 4 for Deep Music Information Dynamics
* The 2020 Joint Conference on AI Music Creativity, October 19-23, 2020, Royal Institute of Technology (KTH), Stockholm, Sweden 
  Access Paper or Ask Questions

Expressive Neural Voice Cloning


Jan 30, 2021
Paarth Neekhara, Shehzeen Hussain, Shlomo Dubnov, Farinaz Koushanfar, Julian McAuley

Figure 1 for Expressive Neural Voice Cloning
Figure 2 for Expressive Neural Voice Cloning
Figure 3 for Expressive Neural Voice Cloning
Figure 4 for Expressive Neural Voice Cloning
* 12 pages, 2 figures, 2 tables 
  Access Paper or Ask Questions

DPD-InfoGAN: Differentially Private Distributed InfoGAN


Oct 24, 2020
Vaikkunth Mugunthan, Vignesh Gokul, Lalana Kagal, Shlomo Dubnov

Figure 1 for DPD-InfoGAN: Differentially Private Distributed InfoGAN
Figure 2 for DPD-InfoGAN: Differentially Private Distributed InfoGAN
Figure 3 for DPD-InfoGAN: Differentially Private Distributed InfoGAN
Figure 4 for DPD-InfoGAN: Differentially Private Distributed InfoGAN

  Access Paper or Ask Questions

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


Aug 04, 2020
Ke Chen, Cheng-i Wang, Taylor Berg-Kirkpatrick, Shlomo Dubnov

Figure 1 for Music SketchNet: Controllable Music Generation via Factorized Representations of Pitch and Rhythm
Figure 2 for Music SketchNet: Controllable Music Generation via Factorized Representations of Pitch and Rhythm
Figure 3 for Music SketchNet: Controllable Music Generation via Factorized Representations of Pitch and Rhythm
Figure 4 for Music SketchNet: Controllable Music Generation via Factorized Representations of Pitch and Rhythm
* 8 pages, 8 figures, Proceedings of the 21st International Society for Music Information Retrieval Conference, ISMIR 2020 
  Access Paper or Ask Questions

Continuous Melody Generation via Disentangled Short-Term Representations and Structural Conditions


Feb 05, 2020
Ke Chen, Gus Xia, Shlomo Dubnov

Figure 1 for Continuous Melody Generation via Disentangled Short-Term Representations and Structural Conditions
Figure 2 for Continuous Melody Generation via Disentangled Short-Term Representations and Structural Conditions
Figure 3 for Continuous Melody Generation via Disentangled Short-Term Representations and Structural Conditions
Figure 4 for Continuous Melody Generation via Disentangled Short-Term Representations and Structural Conditions
* 9 pages, 12 figures, 4 tables. in 14th international conference on semantic computing, ICSC 2020 
  Access Paper or Ask Questions

Query-based Deep Improvisation


Jun 21, 2019
Shlomo Dubnov

Figure 1 for Query-based Deep Improvisation
Figure 2 for Query-based Deep Improvisation
Figure 3 for Query-based Deep Improvisation
Figure 4 for Query-based Deep Improvisation
* 7th International Workshop on Musical Metacreation, International Conference on Computational Creativity 2019 
  Access Paper or Ask Questions

Universal Adversarial Perturbations for Speech Recognition Systems


May 09, 2019
Paarth Neekhara, Shehzeen Hussain, Prakhar Pandey, Shlomo Dubnov, Julian McAuley, Farinaz Koushanfar

Figure 1 for Universal Adversarial Perturbations for Speech Recognition Systems
Figure 2 for Universal Adversarial Perturbations for Speech Recognition Systems
Figure 3 for Universal Adversarial Perturbations for Speech Recognition Systems
Figure 4 for Universal Adversarial Perturbations for Speech Recognition Systems
* 5 Pages, 3 figures 
  Access Paper or Ask Questions

Expediting TTS Synthesis with Adversarial Vocoding


Apr 16, 2019
Paarth Neekhara, Chris Donahue, Miller Puckette, Shlomo Dubnov, Julian McAuley

Figure 1 for Expediting TTS Synthesis with Adversarial Vocoding
Figure 2 for Expediting TTS Synthesis with Adversarial Vocoding
Figure 3 for Expediting TTS Synthesis with Adversarial Vocoding
Figure 4 for Expediting TTS Synthesis with Adversarial Vocoding

  Access Paper or Ask Questions

The Effect of Explicit Structure Encoding of Deep Neural Networks for Symbolic Music Generation


Nov 20, 2018
Ke Chen, Weilin Zhang, Shlomo Dubnov, Gus Xia

Figure 1 for The Effect of Explicit Structure Encoding of Deep Neural Networks for Symbolic Music Generation
Figure 2 for The Effect of Explicit Structure Encoding of Deep Neural Networks for Symbolic Music Generation
Figure 3 for The Effect of Explicit Structure Encoding of Deep Neural Networks for Symbolic Music Generation
Figure 4 for The Effect of Explicit Structure Encoding of Deep Neural Networks for Symbolic Music Generation
* 8 pages, 13 figures 
  Access Paper or Ask Questions

Rethinking Recurrent Latent Variable Model for Music Composition


Oct 07, 2018
Eunjeong Stella Koh, Shlomo Dubnov, Dustin Wright

Figure 1 for Rethinking Recurrent Latent Variable Model for Music Composition
Figure 2 for Rethinking Recurrent Latent Variable Model for Music Composition
Figure 3 for Rethinking Recurrent Latent Variable Model for Music Composition
Figure 4 for Rethinking Recurrent Latent Variable Model for Music Composition
* Published as a conference paper at IEEE MMSP 2018 
  Access Paper or Ask Questions

Adversarial Reprogramming of Sequence Classification Neural Networks


Sep 07, 2018
Paarth Neekhara, Shehzeen Hussain, Shlomo Dubnov, Farinaz Koushanfar

Figure 1 for Adversarial Reprogramming of Sequence Classification Neural Networks
Figure 2 for Adversarial Reprogramming of Sequence Classification Neural Networks
Figure 3 for Adversarial Reprogramming of Sequence Classification Neural Networks
Figure 4 for Adversarial Reprogramming of Sequence Classification Neural Networks
* 10 pages, 5 figures, 2 tables 
  Access Paper or Ask Questions