Andrew J. R. Simpson

According to our database, Andrew J. R. Simpson authored at least 26 papers between 2014 and 2017.

Collaborative distances:

• Dijkstra number of four.
• Erdős number of five.

2017

Two-Stage Single-Channel Audio Source Separation Using Deep Neural Networks.

Emad M. Grais, Gerard Roma, Andrew J. R. Simpson, Mark D. Plumbley

IEEE ACM Trans. Audio Speech Lang. Process., 2017

Psychophysical Evaluation of Audio Source Separation Methods.

Andrew J. R. Simpson, Gerard Roma, Emad M. Grais, Russell D. Mason, Christopher Hummersone, Mark D. Plumbley

Proceedings of the Latent Variable Analysis and Signal Separation, 2017

Discriminative Enhancement for Single Channel Audio Source Separation Using Deep Neural Networks.

Emad M. Grais, Gerard Roma, Andrew J. R. Simpson, Mark D. Plumbley

Proceedings of the Latent Variable Analysis and Signal Separation, 2017

2016

Hierarchical Conflict Propagation: Sequence Learning in a Recurrent Deep Neural Network.

Andrew J. R. Simpson

CoRR, 2016

Combining Mask Estimates for Single Channel Audio Source Separation Using Deep Neural Networks.

Emad M. Grais, Gerard Roma, Andrew J. R. Simpson, Mark D. Plumbley

Proceedings of the Interspeech 2016, 2016

Evaluation of audio source separation models using hypothesis-driven non-parametric statistical methods.

Andrew J. R. Simpson, Gerard Roma, Emad M. Grais, Russell D. Mason, Chris Hummersone, Antoine Liutkus, Mark D. Plumbley

Proceedings of the 24th European Signal Processing Conference, 2016

2015

Deep Remix: Remixing Musical Mixtures Using a Convolutional Deep Neural Network.

Andrew J. R. Simpson, Gerard Roma, Mark D. Plumbley

CoRR, 2015

Qualitative Projection Using Deep Neural Networks.

Andrew J. R. Simpson

CoRR, 2015

Uniform Learning in a Deep Neural Network via "Oddball" Stochastic Gradient Descent.

Andrew J. R. Simpson

CoRR, 2015

"Oddball SGD": Novelty Driven Stochastic Gradient Descent for Training Deep Neural Networks.

Andrew J. R. Simpson

CoRR, 2015

Taming the ReLU with Parallel Dither in a Deep Neural Network.

Andrew J. R. Simpson

CoRR, 2015

Use it or Lose it: Selective Memory and Forgetting in a Perpetual Learning Machine.

Andrew J. R. Simpson

CoRR, 2015

On-the-Fly Learning in a Perpetual Learning Machine.

Andrew J. R. Simpson

CoRR, 2015

Parallel Dither and Dropout for Regularising Deep Neural Networks.

Andrew J. R. Simpson

CoRR, 2015

Dither is Better than Dropout for Regularising Deep Neural Networks.

Andrew J. R. Simpson

CoRR, 2015

Instant Learning: Parallel Deep Neural Networks and Convolutional Bootstrapping.

Andrew J. R. Simpson

CoRR, 2015

Time-Frequency Trade-offs for Audio Source Separation with Binary Masks.

Andrew J. R. Simpson

CoRR, 2015

Deep Transform: Cocktail Party Source Separation via Complex Convolution in a Deep Neural Network.

Andrew J. R. Simpson

CoRR, 2015

Probabilistic Binary-Mask Cocktail-Party Source Separation in a Convolutional Deep Neural Network.

Andrew J. R. Simpson

CoRR, 2015

Deep Transform: Cocktail Party Source Separation via Probabilistic Re-Synthesis.

Andrew J. R. Simpson

CoRR, 2015

Deep Transform: Time-Domain Audio Error Correction via Probabilistic Re-Synthesis.

Andrew J. R. Simpson

CoRR, 2015

Deep Transform: Error Correction via Probabilistic Re-Synthesis.

Andrew J. R. Simpson

CoRR, 2015

Abstract Learning via Demodulation in a Deep Neural Network.

Andrew J. R. Simpson

CoRR, 2015

Over-Sampling in a Deep Neural Network.

Andrew J. R. Simpson

CoRR, 2015

Deep Karaoke: Extracting Vocals from Musical Mixtures Using a Convolutional Deep Neural Network.

Andrew J. R. Simpson, Gerard Roma, Mark D. Plumbley

Proceedings of the Latent Variable Analysis and Signal Separation, 2015

2014

Selectivity and adaptation in the human auditory system.

Andrew J. R. Simpson

PhD thesis, 2014