Mark D. Plumbley
Identifiers
- name variant Mark D. Plumbley 0.60 · backfill
Papers (31)
- Explainable AI in Speaker Recognition -- Making Latent Representations Understandable eess.AS · 2026 · author #3
- DreamAudio: Customized Text-to-Audio Generation with Diffusion Models cs.SD · 2025 · author #7
- Sound Event Detection with Sequentially Labelled Data Based on Connectionist Temporal Classification and Unsupervised Clustering cs.SD · 2019 · author #4
- Cross-task learning for audio tagging, sound event detection spatial localization: DCASE 2019 baseline systems cs.SD · 2019 · author #6
- Cross-task learning for audio tagging, sound event detection and spatial localization: DCASE 2019 baseline systems cs.SD · 2019 · author #6
- Fast Iterative Shrinkage for Signal Declipping and Dequantization eess.SP · 2018 · author #4
- Referenceless Performance Evaluation of Audio Source Separation using Deep Neural Networks cs.SD · 2018 · author #5
- Raw Multi-Channel Audio Source Separation using Multi-Resolution Convolutional Auto-Encoders cs.SD · 2018 · author #3
- Multi-Resolution Fully Convolutional Neural Networks for Monaural Audio Source Separation cs.SD · 2017 · author #4
- Large-scale weakly supervised audio classification using gated convolutional neural network cs.SD · 2017 · author #4
- Surrey-cvssp system for DCASE2017 challenge task4 cs.SD · 2017 · author #4
- Single Channel Audio Source Separation using Convolutional Denoising Autoencoders cs.SD · 2017 · author #2
- Attention and Localization based on a Deep Convolutional Recurrent Model for Weakly Supervised Audio Tagging cs.SD · 2017 · author #5
- Convolutional Gated Recurrent Neural Network Incorporating Spatial Features for Audio Tagging cs.SD · 2017 · author #5
- Discriminative Enhancement for Single Channel Audio Source Separation using Deep Neural Networks cs.SD · 2016 · author #4
- Automatic Environmental Sound Recognition: Performance versus Computational Cost cs.SD · 2016 · author #4
- Hierarchical learning for DNN-based acoustic scene classification cs.SD · 2016 · author #4
- Unsupervised Feature Learning Based on Deep Models for Environmental Audio Tagging cs.SD · 2016 · author #7
- Fully DNN-based Multi-label regression for audio tagging cs.CV · 2016 · author #5
- Deep Remix: Remixing Musical Mixtures Using a Convolutional Deep Neural Network cs.SD · 2015 · author #3
- Deep Karaoke: Extracting Vocals from Musical Mixtures Using a Convolutional Deep Neural Network cs.SD · 2015 · author #3
- Acoustic Scene Classification cs.SD · 2014 · author #4
- Automatic large-scale classification of bird sounds is strongly improved by unsupervised feature learning cs.SD · 2014 · author #2
- Large-scale analysis of frequency modulation in birdsong databases cs.SD · 2013 · author #2
- An open dataset for research on audio field recording archives: freefield1010 cs.SD · 2013 · author #2
- Improved multiple birdsong tracking with distribution derivative method and Markov renewal process clustering cs.SD · 2013 · author #4
- Segregating event streams and noise with a Markov renewal process model cs.AI · 2012 · author #2
- Predictive Information Rate in Discrete-time Gaussian Processes stat.ML · 2012 · author #2
- Analysis-based sparse reconstruction with synthesis-based solvers cs.IT · 2012 · author #3
- A measure of statistical complexity based on predictive information math.ST · 2010 · author #2
- Polar Polytopes and Recovery of Sparse Representations cs.IT · 2005 · author #1
Mentions
Frequent Coauthors
- Wenwu Wang 12 shared papers
- Yong Xu 9 shared papers
- Qiuqiang Kong 7 shared papers
- Dan Stowell 6 shared papers
- Emad M. Grais 5 shared papers
- Qiang Huang 5 shared papers
- Dominic Ward 3 shared papers
- Gerard Roma 3 shared papers
- Andrew J.R. Simpson 2 shared papers
- Hagen Wierstorf 2 shared papers
- Philip J. B. Jackson 2 shared papers
- Samer A. Abdallah 2 shared papers
- Siddharth Sigtia 2 shared papers
- Turab Iqbal 2 shared papers
- Yin Cao 2 shared papers
- Adam M. Stark 1 shared papers
- Andrew J.R Simpson 1 shared papers
- Daniele Barchiesi 1 shared papers
- Dimitrios Giannoulis 1 shared papers
- Francis Bach 1 shared papers