Get started
Author

Cem Subakan

Attention Is All You Need In Speech Separation
2021 · Cem Subakan, Mirco Ravanelli, et al. · IEEE International Conference on Acoustics Speech and Signal Processing · 695
SpeechBrain: A General-Purpose Speech Toolkit
2021 · Ravanelli, Mirco, Parcollet, Titouan, et al. · arXiv (Cornell University) · 505
PDF
Two-Step Sound Source Separation: Training On Learned Latent Targets
2020 · Efthymios Tzinis, Shrikant Venkataramani, et al. · IEEE International Conference on Acoustics Speech and Signal Processing · 67
PDF
Exploring Self-Attention Mechanisms for Speech Separation
2023 · Cem Subakan, Mirco Ravanelli, et al. · IEEE/ACM Transactions on Audio Speech and Language Processing · 49
CommonAccent: Exploring Large Acoustic Pretrained Models for Accent Classification Based on Common Voice
2023 · Juan Zuluaga-Gomez, Sara Ahmed, et al. · Interspeech (USB) · 24
PDF
Resource-Efficient Separation Transformer
2024 · Luca Della Libera, Cem Subakan, et al. · IEEE International Conference on Acoustics Speech and Signal Processing · 22
PDF
Continual Learning of New Sound Classes Using Generative Replay
2019 · Zhepei Wang, Cem Subakan, et al. · IEEE Workshop on Applications of Signal Processing to Audio and Acoustics (WASPAA) · 22
PDF
Self-Supervised Learning for Infant Cry Analysis
2023 · Arsenii Gorin, Cem Subakan, et al. · IEEE International Conference on Acoustics, Speech, and Signal Processing Workshops (ICASSPW) · 20
PDF
Real-M: Towards Speech Separation on Real Mixtures
2022 · Cem Subakan, Mirco Ravanelli, et al. · IEEE International Conference on Acoustics Speech and Signal Processing · 20
Learning Representations for New Sound Classes With Continual Self-Supervised Learning
2022 · Zhepei Wang, Cem Subakan, et al. · IEEE Signal Processing Letters · 18
PDF
CryCeleb: A Speaker Verification Dataset Based on Infant Cry Sounds
2024 · David Budaghyan, Charles C. Onu, et al. · IEEE International Conference on Acoustics Speech and Signal Processing · 17
PDF
Neural network alternatives toconvolutive audio models for source separation
2017 · Shrikant Venkataramani, Cem Subakan, et al. · Machine learning for signal processing ... · 14
Attention is All You Need in Speech Separation
2020 · Subakan, Cem, Ravanelli, Mirco, et al. · arXiv (Cornell University) · 10
PDF
How Should We Extract Discrete Audio Tokens from Self-Supervised Models?
2024 · Pooneh Mousavi, Jarod Duret, et al. · Interspeech (USB) · 9
PDF
Spectral Learning of Mixture of Hidden Markov Models
2014 · Cem Subakan, Johannes Traa, et al. · neural information processing systems · 9
Generative Adversarial Source Separation
2017 · Subakan, Cem, Smaragdis, Paris · arXiv (Cornell University) · 8
PDF
A Generative Modeling Approach for Interpreting Population-Level Variability in Brain Structure
2020 · Ran Liu, Cem Subakan, et al. · Lecture notes in computer science · 7
PDF
CL-MASR: A Continual Learning Benchmark for Multilingual ASR
2024 · Luca Della Libera, Pooneh Mousavi, et al. · IEEE/ACM Transactions on Audio Speech and Language Processing · 6
Investigating the Effectiveness of Explainability Methods in Parkinson’s Detection from Speech
2025 · Eleonora Mancini, Francesco Paissan, et al. · IEEE International Conference on Acoustics, Speech, and Signal Processing Workshops (ICASSPW) · 5
PDF
Audio Editing with Non-Rigid Text Prompts
2024 · Francesco Paissan, Luca Della Libera, et al. · Interspeech (USB) · 5
PDF
Phoneme Discretized Saliency Maps for Explainable Detection of AI-Generated Voice
2024 · Shubham Gupta, Mirco Ravanelli, et al. · Interspeech (USB) · 4
PDF
Artificial Neural Networks in Pattern Recognition
2024 · Ching Yee Suen, Adam Krzyzak, et al. · Lecture notes in computer science · 4
CL-MASR: A Continual Learning Benchmark for Multilingual ASR
2023 · Luca Della Libera, Pooneh Mousavi, et al. · 4
Posthoc Interpretation via Quantization
2023 · Paissan, Francesco, Subakan, Cem, et al. · arXiv (Cornell University) · 4
PDF
Planing It by Ear: Convolutional Neural Networks for Acoustic Anomaly Detection in Industrial Wood Planers
2025 · Anthony Deschênes, Rémi Georges, et al. · IEEE International Conference on Acoustics Speech and Signal Processing · 3
PDF
Works count: 82
Citation count: 1,575
H-index: 12
I10-index: 13
Year
Topic
Type