Paris Smaragdis

225 papers A* 4A 9B 1Misc 43Journal 95Unranked 69

Year	Rank	Type	Title / Venue / Authors
2026	J	`jnl`	Gencho: Room Impulse Response Generation from Reverberant Speech and Text via Diffusion Transformers. CoRR Jackie Lin, Jiaqi Su, Nishit Anand, Zeyu Jin, Minje Kim, Paris Smaragdis
2025	—	`conf`	Adaptive Slimming for Scalable and Efficient Speech Enhancement. WASPAA Riccardo Miccini, Minje Kim, Clément Laroche, Luca Pezzarossa, Paris Smaragdis
2025	J	`jnl`	Adaptive Slimming for Scalable and Efficient Speech Enhancement. CoRR Riccardo Miccini, Minje Kim, Clément Laroche, Luca Pezzarossa, Paris Smaragdis
2025	—	`conf`	Combolutional Neural Networks. WASPAA Cameron Churchwell, Minje Kim, Paris Smaragdis
2025	J	`jnl`	Combolutional Neural Networks. CoRR Cameron Churchwell, Minje Kim, Paris Smaragdis
2025	—	`conf`	Continuous-Time Signal Decomposition: An Implicit Neural Generalization of PCA and ICA. MLSP Shayan K. Azmoodeh, Krishna Subramani, Paris Smaragdis
2025	J	`jnl`	Continuous-Time Signal Decomposition: An Implicit Neural Generalization of PCA and ICA. CoRR Shayan K. Azmoodeh, Krishna Subramani, Paris Smaragdis
2025	—	`conf`	Generative Data Augmentation Challenge: Synthesis of Room Acoustics for Speaker Distance Estimation. ICASSP Workshops Jackie Lin, Georg Götz, Hermes Sampedro Llopis, Haukur Hafsteinsson, Steinar Guðjónsson, Daniel Gert Nielsen, Finnur Pind, Paris Smaragdis, Dinesh Manocha, John R. Hershey, Trausti T. Kristjansson, Minje Kim
2025	J	`jnl`	Generative Data Augmentation Challenge: Synthesis of Room Acoustics for Speaker Distance Estimation. CoRR Jackie Lin, Georg Götz, Hermes Sampedro Llopis, Haukur Hafsteinsson, Steinar Guðjónsson, Daniel Gert Nielsen, Finnur Pind, Paris Smaragdis, Dinesh Manocha, John R. Hershey, Trausti T. Kristjansson, Minje Kim
2025	—	`conf`	Learning to Upsample and Upmix Audio in the Latent Domain. WASPAA Dimitrios Bralios, Paris Smaragdis, Jonah Casebeer
2025	J	`jnl`	Learning to Upsample and Upmix Audio in the Latent Domain. CoRR Dimitrios Bralios, Paris Smaragdis, Jonah Casebeer
2025	Misc	`conf`	On Class Separability Pitfalls In Audio-Text Contrastive Zero-Shot Learning. ICASSP Tiago Fernandes Tavares, Fábio José Ayres, Zhepei Wang, Paris Smaragdis
2025	J	`jnl`	PromptSep: Generative Audio Separation via Multimodal Prompting. CoRR Yutong Wen, Ke Chen, Prem Seetharaman, Oriol Nieto, Jiaqi Su, Rithesh Kumar, Minje Kim, Paris Smaragdis, Zeyu Jin, Justin Salamon
2025	—	`conf`	Re-Bottleneck: Latent Re-Structuring for Neural Audio Autoencoders. MLSP Dimitrios Bralios, Jonah Casebeer, Paris Smaragdis
2025	J	`jnl`	Re-Bottleneck: Latent Re-Structuring for Neural Audio Autoencoders. CoRR Dimitrios Bralios, Jonah Casebeer, Paris Smaragdis
2025	—	`conf`	Rethinking Non-Negative Matrix Factorization with Implicit Neural Representations. WASPAA Krishna Subramani, Paris Smaragdis, Takuya Higuchi, Mehrez Souden
2025	—	`conf`	User-Guided Generative Source Separation. ISMIR Yutong Wen, Minje Kim, Paris Smaragdis
2025	J	`jnl`	User-guided Generative Source Separation. CoRR Yutong Wen, Minje Kim, Paris Smaragdis
2024	A	`conf`	Audio Editing with Non-Rigid Text Prompts. INTERSPEECH Francesco Paissan, Luca Della Libera, Zhepei Wang, Paris Smaragdis, Mirco Ravanelli, Cem Subakan
2024	J	`jnl`	Measuring similarity between embedding spaces using induced neighborhood graphs. CoRR Tiago Tavares, Fábio J. Ayres, Paris Smaragdis
2024	Misc	`conf`	Meta-AF Echo Cancellation for Improved Keyword Spotting. ICASSP Jonah Casebeer, Junkai Wu, Paris Smaragdis
2024	Misc	`conf`	Noise-Robust DSP-Assisted Neural Pitch Estimation With Very Low Complexity. ICASSP Krishna Subramani, Jean-Marc Valin, Jan Büthe, Paris Smaragdis, Mike Goodwin
2024	J	`jnl`	On Class Separability Pitfalls In Audio-Text Contrastive Zero-Shot Learning. CoRR Tiago Tavares, Fábio J. Ayres, Zhepei Wang, Paris Smaragdis
2024	J	`jnl`	Rethinking Non-Negative Matrix Factorization with Implicit Neural Representations. CoRR Krishna Subramani, Paris Smaragdis, Takuya Higuchi, Mehrez Souden
2024	J	`jnl`	Scaling Up Adaptive Filter Optimizers. CoRR Jonah Casebeer, Nicholas J. Bryan, Paris Smaragdis
2024	—	`conf`	Sound Source Separation Using Latent Variational Block-Wise Disentanglement. ICASSP Workshops Karim Helwani, Masahito Togami, Paris Smaragdis, Michael M. Goodwin
2024	J	`jnl`	Sound Source Separation Using Latent Variational Block-Wise Disentanglement. CoRR Karim Helwani, Masahito Togami, Paris Smaragdis, Michael M. Goodwin
2023	Misc	`conf`	A Framework for Unified Real-Time Personalized and Non-Personalized Speech Enhancement. ICASSP Zhepei Wang, Ritwik Giri, Devansh Shah, Jean-Marc Valin, Michael M. Goodwin, Paris Smaragdis
2023	J	`jnl`	A Framework for Unified Real-time Personalized and Non-Personalized Speech Enhancement. CoRR Zhepei Wang, Ritwik Giri, Devansh Shah, Jean-Marc Valin, Michael M. Goodwin, Paris Smaragdis
2023	J	`jnl`	Audio Editing with Non-Rigid Text Prompts. CoRR Francesco Paissan, Zhepei Wang, Mirco Ravanelli, Paris Smaragdis, Cem Subakan
2023	J	`jnl`	Audio Signal Processing in the 21st Century: The important outcomes of the past 25 years. IEEE Signal Process. Mag. Gaël Richard, Paris Smaragdis, Sharon Gannot, Patrick A. Naylor, Shoji Makino, Walter Kellermann, Akihiko Sugiyama
2023	—	`conf`	Complete and Separate: Conditional Separation with Missing Target Source Attribute Completion. WASPAA Dimitrios Bralios, Efthymios Tzinis, Paris Smaragdis
2023	J	`jnl`	Complete and separate: Conditional separation with missing target source attribute completion. CoRR Dimitrios Bralios, Efthymios Tzinis, Paris Smaragdis
2023	Misc	`conf`	Framewise Wavegan: High Speed Adversarial Vocoder In Time Domain With Very Low Computational Complexity. ICASSP Ahmed Mustafa, Jean-Marc Valin, Jan Büthe, Paris Smaragdis, Mike Goodwin
2023	Misc	`conf`	Generative Modeling Based Manifold Learning for Adaptive Filtering Guidance. ICASSP Karim Helwani, Paris Smaragdis, Michael M. Goodwin
2023	Misc	`conf`	Latent Iterative Refinement for Modular Source Separation. ICASSP Dimitrios Bralios, Efthymios Tzinis, Gordon Wichern, Paris Smaragdis, Jonathan Le Roux
2023	—	`conf`	Low-Complexity Streaming Speech Super-Resolution. MLSP Erfan Soltanmohammadi, Paris Smaragdis, Michael M. Goodwin
2023	J	`jnl`	Mechatronic Generation of Datasets for Acoustics Research. CoRR Austin Lu, Ethaniel Moore, Arya Nallanthighall, Kanad Sarkar, Manan Mittal, Ryan M. Corey, Paris Smaragdis, Andrew C. Singer
2023	J	`jnl`	Meta-AF Echo Cancellation for Improved Keyword Spotting. CoRR Jonah Casebeer, Junkai Wu, Paris Smaragdis
2023	J	`jnl`	Meta-AF: Meta-Learning for Adaptive Filters. IEEE ACM Trans. Audio Speech Lang. Process. Jonah Casebeer, Nicholas J. Bryan, Paris Smaragdis
2023	J	`jnl`	Noise-Robust DSP-Assisted Neural Pitch Estimation with Very Low Complexity. CoRR Krishna Subramani, Jean-Marc Valin, Jan Büthe, Paris Smaragdis, Mike Goodwin
2023	Misc	`conf`	Optimal Condition Training for Target Source Separation. ICASSP Efthymios Tzinis, Gordon Wichern, Paris Smaragdis, Jonathan Le Roux
2023	—	`conf`	Unsupervised Improvement of Audio-Text Cross-Modal Representations. WASPAA Zhepei Wang, Cem Subakan, Krishna Subramani, Junkai Wu, Tiago Tavares, Fábio J. Ayres, Paris Smaragdis
2023	J	`jnl`	Unsupervised Improvement of Audio-Text Cross-Modal Representations. CoRR Zhepei Wang, Cem Subakan, Krishna Subramani, Junkai Wu, Tiago Tavares, Fábio J. Ayres, Paris Smaragdis
2022	J	`jnl`	Compute and Memory Efficient Universal Sound Source Separation. J. Signal Process. Syst. Efthymios Tzinis, Zhepei Wang, Xilin Jiang, Paris Smaragdis
2022	J	`jnl`	Don't Look Up: Ubiquitous Data Exfiltration Pathways in Commercial Spaces. CoRR Anku Adhikari, Samuel Guo, Paris Smaragdis, Marianne Winslett
2022	A	`conf`	End-to-end LPCNet: A Neural Vocoder With Fully-Differentiable LPC Estimation. INTERSPEECH Krishna Subramani, Jean-Marc Valin, Umut Isik, Paris Smaragdis, Arvindh Krishnaswamy
2022	J	`jnl`	End-to-end LPCNet: A Neural Vocoder With Fully-Differentiable LPC Estimation. CoRR Krishna Subramani, Jean-Marc Valin, Umut Isik, Paris Smaragdis, Arvindh Krishnaswamy
2022	J	`jnl`	Framewise WaveGAN: High Speed Adversarial Vocoder in Time Domain with Very Low Computational Complexity. CoRR Ahmed Mustafa, Jean-Marc Valin, Jan Büthe, Paris Smaragdis, Mike Goodwin
2022	A	`conf`	Heterogeneous Target Speech Separation. INTERSPEECH Efthymios Tzinis, Gordon Wichern, Aswin Shanmugam Subramanian, Paris Smaragdis, Jonathan Le Roux
2022	J	`jnl`	Heterogeneous Target Speech Separation. CoRR Efthymios Tzinis, Gordon Wichern, Aswin Shanmugam Subramanian, Paris Smaragdis, Jonathan Le Roux
2022	J	`jnl`	Latent Iterative Refinement for Modular Source Separation. CoRR Dimitrios Bralios, Efthymios Tzinis, Gordon Wichern, Paris Smaragdis, Jonathan Le Roux
2022	J	`jnl`	Learning Representations for New Sound Classes With Continual Self-Supervised Learning. CoRR Zhepei Wang, Cem Subakan, Xilin Jiang, Junkai Wu, Efthymios Tzinis, Mirco Ravanelli, Paris Smaragdis
2022	J	`jnl`	Learning Representations for New Sound Classes With Continual Self-Supervised Learning. IEEE Signal Process. Lett. Zhepei Wang, Cem Subakan, Xilin Jiang, Junkai Wu, Efthymios Tzinis, Mirco Ravanelli, Paris Smaragdis
2022	—	`conf`	Mechatronic Generation of Datasets for Acoustics Research. IWAENC Austin Lu, Ethaniel Moore, Arya Nallanthighall, Kanad Sarkar, Manan Mittal, Ryan M. Corey, Paris Smaragdis, Andrew C. Singer
2022	J	`jnl`	Meta-AF: Meta-Learning for Adaptive Filters. CoRR Jonah Casebeer, Nicholas J. Bryan, Paris Smaragdis
2022	J	`jnl`	Meta-Learning for Adaptive Filters with Higher-Order Frequency Dependencies. CoRR Junkai Wu, Jonah Casebeer, Nicholas J. Bryan, Paris Smaragdis
2022	—	`conf`	Meta-Learning for Adaptive Filters with higher-order Frequency Dependencies. IWAENC Junkai Wu, Jonah Casebeer, Nicholas J. Bryan, Paris Smaragdis
2022	J	`jnl`	Neural Speech Synthesis on a Shoestring: Improving the Efficiency of LPCNet. CoRR Jean-Marc Valin, Umut Isik, Paris Smaragdis, Arvindh Krishnaswamy
2022	Misc	`conf`	Neural Speech Synthesis on a Shoestring: Improving the Efficiency of Lpcnet. ICASSP Jean-Marc Valin, Umut Isik, Paris Smaragdis, Arvindh Krishnaswamy
2022	J	`jnl`	Optimal Condition Training for Target Source Separation. CoRR Efthymios Tzinis, Gordon Wichern, Paris Smaragdis, Jonathan Le Roux
2022	A	`conf`	Real-Time Packet Loss Concealment With Mixed Generative and Predictive Model. INTERSPEECH Jean-Marc Valin, Ahmed Mustafa, Christopher Montgomery, Timothy B. Terriberry, Michael Klingbeil, Paris Smaragdis, Arvindh Krishnaswamy
2022	J	`jnl`	Real-Time Packet Loss Concealment With Mixed Generative and Predictive Model. CoRR Jean-Marc Valin, Ahmed Mustafa, Christopher Montgomery, Timothy B. Terriberry, Michael Klingbeil, Paris Smaragdis, Arvindh Krishnaswamy
2022	J	`jnl`	RemixIT: Continual Self-Training of Speech Enhancement Models via Bootstrapped Remixing. IEEE J. Sel. Top. Signal Process. Efthymios Tzinis, Yossi Adi, Vamsi K. Ithapu, Buye Xu, Paris Smaragdis, Anurag Kumar
2022	J	`jnl`	RemixIT: Continual self-training of speech enhancement models via bootstrapped remixing. CoRR Efthymios Tzinis, Yossi Adi, Vamsi Krishna Ithapu, Buye Xu, Paris Smaragdis, Anurag Kumar
2022	J	`jnl`	Semi-supervised Time Domain Target Speaker Extraction with Attention. CoRR Zhepei Wang, Ritwik Giri, Shrikant Venkataramani, Umut Isik, Jean-Marc Valin, Paris Smaragdis, Michael M. Goodwin, Arvindh Krishnaswamy
2021	—	`conf`	Auto-DSP: Learning to Optimize Acoustic Echo Cancellers. WASPAA Jonah Casebeer, Nicholas J. Bryan, Paris Smaragdis
2021	J	`jnl`	Auto-DSP: Learning to Optimize Acoustic Echo Cancellers. CoRR Jonah Casebeer, Nicholas J. Bryan, Paris Smaragdis
2021	Misc	`conf`	Communication-Cost Aware Microphone Selection for Neural Speech Enhancement with Ad-Hoc Microphone Arrays. ICASSP Jonah Casebeer, Jamshed Kaikaus, Paris Smaragdis
2021	J	`jnl`	Compute and memory efficient universal sound source separation. CoRR Efthymios Tzinis, Zhepei Wang, Xilin Jiang, Paris Smaragdis
2021	Misc	`conf`	Differentiable Signal Processing With Black-Box Audio Effects. ICASSP Marco A. Martínez Ramírez, Oliver Wang, Paris Smaragdis, Nicholas J. Bryan
2021	J	`jnl`	Differentiable Signal Processing With Black-Box Audio Effects. CoRR Marco A. Martínez Ramírez, Oliver Wang, Paris Smaragdis, Nicholas J. Bryan
2021	Misc	`conf`	Optimizing Short-Time Fourier Transform Parameters via Gradient Descent. ICASSP An Zhao, Krishna Subramani, Paris Smaragdis
2021	—	`conf`	Point Cloud Audio Processing. WASPAA Krishna Subramani, Paris Smaragdis
2021	J	`jnl`	Point Cloud Audio Processing. CoRR Krishna Subramani, Paris Smaragdis
2021	—	`conf`	Separate But Together: Unsupervised Federated Learning for Speech Enhancement from Non-IID Data. WASPAA Efthymios Tzinis, Jonah Casebeer, Zhepei Wang, Paris Smaragdis
2021	J	`jnl`	Separate but Together: Unsupervised Federated Learning for Speech Enhancement from Non-IID Data. CoRR Efthymios Tzinis, Jonah Casebeer, Zhepei Wang, Paris Smaragdis
2021	—	`conf`	Sound Event Detection with Adaptive Frequency Selection. WASPAA Zhepei Wang, Jonah Casebeer, Adam Clemmitt, Efthymios Tzinis, Paris Smaragdis
2021	J	`jnl`	Sound Event Detection with Adaptive Frequency Selection. CoRR Zhepei Wang, Jonah Casebeer, Adam Clemmitt, Efthymios Tzinis, Paris Smaragdis
2021	Misc	`conf`	Unified Gradient Reweighting for Model Biasing with Applications to Source Separation. ICASSP Efthymios Tzinis, Dimitrios Bralios, Paris Smaragdis
2020	J	`jnl`	Communication-Cost Aware Microphone Selection For Neural Speech Enhancement with Ad-hoc Microphone Arrays. CoRR Jonah Casebeer, Jamshed Kaikaus, Paris Smaragdis
2020	Misc	`conf`	End-To-End Non-Negative Autoencoders for Sound Source Separation. ICASSP Shrikant Venkataramani, Efthymios Tzinis, Paris Smaragdis
2020	Misc	`conf`	One-Shot Parametric Audio Production Style Transfer with Application to Frequency Equalization. ICASSP Stylianos I. Mimilakis, Nicholas J. Bryan, Paris Smaragdis
2020	J	`jnl`	Optimizing Short-Time Fourier Transform Parameters via Gradient Descent. CoRR An Zhao, Krishna Subramani, Paris Smaragdis
2020	J	`jnl`	Self-supervised Learning for Speech Enhancement. CoRR Yu-Che Wang, Shrikant Venkataramani, Paris Smaragdis
2020	—	`conf`	Sudo RM -RF: Efficient Networks for Universal Audio Source Separation. MLSP Efthymios Tzinis, Zhepei Wang, Paris Smaragdis
2020	J	`jnl`	Sudo rm -rf: Efficient Networks for Universal Audio Source Separation. CoRR Efthymios Tzinis, Zhepei Wang, Paris Smaragdis
2020	Misc	`conf`	Two-Step Sound Source Separation: Training On Learned Latent Targets. ICASSP Efthymios Tzinis, Shrikant Venkataramani, Zhepei Wang, Y. Cem Sübakan, Paris Smaragdis
2020	J	`jnl`	Unified Gradient Reweighting for Model Biasing with Applications to Source Separation. CoRR Efthymios Tzinis, Dimitrios Bralios, Paris Smaragdis
2019	—	`conf`	A Style Transfer Approach to Source Separation. WASPAA Shrikant Venkataramani, Efthymios Tzinis, Paris Smaragdis
2019	J	`jnl`	A Style Transfer Approach to Source Separation. CoRR Shrikant Venkataramani, Efthymios Tzinis, Paris Smaragdis
2019	—	`conf`	Continual Learning of New Sound Classes Using Generative Replay. WASPAA Zhepei Wang, Y. Cem Sübakan, Efthymios Tzinis, Paris Smaragdis, Laurent Charlin
2019	J	`jnl`	Continual Learning of New Sound Classes using Generative Replay. CoRR Zhepei Wang, Y. Cem Sübakan, Efthymios Tzinis, Paris Smaragdis, Laurent Charlin
2019	—	`conf`	Deep Tensor Factorization for Spatially-Aware Scene Decomposition. WASPAA Jonah Casebeer, Michael Colomb, Paris Smaragdis
2019	J	`jnl`	Deep Tensor Factorization for Spatially-Aware Scene Decomposition. CoRR Jonah Casebeer, Michael Colomb, Paris Smaragdis
2019	J	`jnl`	End-to-end Non-Negative Autoencoders for Sound Source Separation. CoRR Shrikant Venkataramani, Efthymios Tzinis, Paris Smaragdis
2019	Misc	`conf`	Majorization-minimization Algorithms for Convolutive NMF with the Beta-divergence. ICASSP Dylan Fagot, Herwig Wendt, Cédric Févotte, Paris Smaragdis
2019	Misc	`conf`	Multi-view Networks for Multi-channel Audio Classification. ICASSP Jonah Casebeer, Zhepei Wang, Paris Smaragdis
2019	J	`jnl`	Two-Step Sound Source Separation: Training on Learned Latent Targets. CoRR Efthymios Tzinis, Shrikant Venkataramani, Zhepei Wang, Y. Cem Sübakan, Paris Smaragdis
2019	Misc	`conf`	Unsupervised Deep Clustering for Source Separation: Direct Learning from Mixtures Using Spatial Information. ICASSP Efthymios Tzinis, Shrikant Venkataramani, Paris Smaragdis
2019	A*	`conf`	VoiceAssist: Guiding Users to High-Quality Voice Recordings. CHI Prem Seetharaman, Gautham J. Mysore, Bryan Pardo, Paris Smaragdis, Celso Gomes
2018	—	`ch.`	Audition for multimedia computing. Frontiers of Multimedia Research Gerald Friedland, Paris Smaragdis, Josh H. McDermott, Bhiksha Raj
2018	Misc	`conf`	Bitwise Neural Networks for Efficient Single-Channel Source Separation. ICASSP Minje Kim, Paris Smaragdis
2018	Misc	`conf`	Blind Estimation of the Speech Transmission Index for Speech Quality Prediction. ICASSP Prem Seetharaman, Gautham J. Mysore, Paris Smaragdis, Bryan Pardo
2018	Misc	`conf`	End-To-End Source Separation With Adaptive Front-Ends. ACSSC Shrikant Venkataramani, Jonah Casebeer, Paris Smaragdis
2018	J	`jnl`	End-to-end Networks for Supervised Single-channel Speech Separation. CoRR Shrikant Venkataramani, Paris Smaragdis
2018	Misc	`conf`	Generative Adversarial Source Separation. ICASSP Y. Cem Sübakan, Paris Smaragdis
2018	J	`jnl`	Learning the Base Distribution in Implicit Generative Models. CoRR Y. Cem Sübakan, Oluwasanmi Koyejo, Paris Smaragdis
2018	J	`jnl`	Multi-View Networks For Multi-Channel Audio Classification. CoRR Jonah Casebeer, Zhepei Wang, Paris Smaragdis
2018	—	`conf`	Multi-View Networks for Denoising of Arbitrary Numbers of Channels. IWAENC Jonah Casebeer, Brian Luc, Paris Smaragdis
2018	J	`jnl`	Multi-View Networks for Denoising of Arbitrary Numbers of Channels. CoRR Jonah Casebeer, Brian Luc, Paris Smaragdis
2018	—	`conf`	Performance Based Cost Functions for End-to-End Speech Separation. APSIPA Shrikant Venkataramani, Ryley Higa, Paris Smaragdis
2018	J	`jnl`	Performance Based Cost Functions for End-to-End Speech Separation. CoRR Shrikant Venkataramani, Ryley Higa, Paris Smaragdis
2018	J	`jnl`	Unsupervised Deep Clustering for Source Separation: Direct Learning from Mixtures using Spatial Information. CoRR Efthymios Tzinis, Shrikant Venkataramani, Paris Smaragdis
2017	J	`jnl`	A State-Space Approach to Dynamic Nonnegative Matrix Factorization. CoRR Nasser Mohammadiha, Paris Smaragdis, Ghazaleh Panahandeh, Simon Doclo
2017	Misc	`conf`	A neural network alternative to non-negative audio models. ICASSP Paris Smaragdis, Shrikant Venkataramani
2017	A*	`conf`	AutoDub: Automatic Redubbing for Voiceover Editing. UIST Shrikant Venkataramani, Paris Smaragdis, Gautham J. Mysore
2017	J	`jnl`	Diagonal RNNs in Symbolic Music Modeling. CoRR Y. Cem Sübakan, Paris Smaragdis
2017	—	`conf`	Diagonal rnns in symbolic music modeling. WASPAA Y. Cem Sübakan, Paris Smaragdis
2017	J	`jnl`	End-to-end Source Separation with Adaptive Front-Ends. CoRR Shrikant Venkataramani, Paris Smaragdis
2017	J	`jnl`	Generative Adversarial Source Separation. CoRR Y. Cem Sübakan, Paris Smaragdis
2017	J	`jnl`	Neural Network Alternatives to Convolutive Audio Models for Source Separation. CoRR Shrikant Venkataramani, Y. Cem Sübakan, Paris Smaragdis
2017	—	`conf`	Neural network alternatives toconvolutive audio models for source separation. MLSP Shrikant Venkataramani, Y. Cem Sübakan, Paris Smaragdis
2017	J	`jnl`	Supervised and Unsupervised Speech Enhancement Using Nonnegative Matrix Factorization. CoRR Nasser Mohammadiha, Paris Smaragdis, Arne Leijon
2017	—	`conf`	Towards end-to-end polyphonic music transcription: Transforming music audio directly to a score. WASPAA Ralf Gunter Correa Carvalho, Paris Smaragdis
2016	J	`jnl`	A Neural Network Alternative to Non-Negative Audio Models. CoRR Paris Smaragdis, Shrikant Venkataramani
2016	J	`jnl`	Bitwise Neural Networks. CoRR Minje Kim, Paris Smaragdis
2016	Misc	`conf`	Efficient neighborhood-based topic modeling for collaborative audio enhancement on massive crowdsourced recordings. ICASSP Minje Kim, Paris Smaragdis
2016	J	`jnl`	NoiseOut: A Simple Way to Prune Neural Networks. CoRR Mohammad Babaeizadeh, Paris Smaragdis, Roy H. Campbell
2016	J	`jnl`	Robust Source Localization and Enhancement With a Probabilistic Steered Response Power Model. IEEE ACM Trans. Audio Speech Lang. Process. Johannes Traa, David Wingate, Noah D. Stein, Paris Smaragdis
2015	J	`jnl`	A Dictionary Learning Approach for Factorial Gaussian Models. CoRR Y. Cem Sübakan, Johannes Traa, Paris Smaragdis, Noah D. Stein
2015	J	`jnl`	A State-Space Approach to Dynamic Nonnegative Matrix Factorization. IEEE Trans. Signal Process. Nasser Mohammadiha, Paris Smaragdis, Ghazaleh Panahandeh, Simon Doclo
2015	—	`conf`	Adaptive Denoising Autoencoders: A Fine-Tuning Scheme to Learn from Test Mixtures. LVA/ICA Minje Kim, Paris Smaragdis
2015	J	`jnl`	Compositional Models for Audio Processing: Uncovering the structure of sound mixtures. IEEE Signal Process. Mag. Tuomas Virtanen, Jort Florent Gemmeke, Bhiksha Raj, Paris Smaragdis
2015	—	`conf`	Directional NMF for joint source localization and separation. WASPAA Johannes Traa, Paris Smaragdis, Noah D. Stein, David Wingate
2015	Misc	`conf`	Efficient manifold preserving audio source separation using locality sensitive hashing. ICASSP Minje Kim, Paris Smaragdis, Gautham J. Mysore
2015	J	`jnl`	Guest Editorial: Machine Learning for Signal Processing. J. Signal Process. Syst. Saeid Sanei, Paris Smaragdis, Anthony T. S. Ho, Asoke K. Nandi, Jan Larsen
2015	J	`jnl`	Joint Optimization of Masks and Deep Recurrent Neural Networks for Monaural Source Separation. CoRR Po-Sen Huang, Minje Kim, Mark Hasegawa-Johnson, Paris Smaragdis
2015	J	`jnl`	Joint Optimization of Masks and Deep Recurrent Neural Networks for Monaural Source Separation. IEEE ACM Trans. Audio Speech Lang. Process. Po-Sen Huang, Minje Kim, Mark Hasegawa-Johnson, Paris Smaragdis
2015	Misc	`conf`	Joint acoustic and spectral modeling for speech dereverberation using non-negative representations. ICASSP Nasser Mohammadiha, Paris Smaragdis, Simon Doclo
2015	—	`conf`	Method of moments learning for left-to-right Hidden Markov models. WASPAA Y. Cem Sübakan, Johannes Traa, Paris Smaragdis, Daniel J. Hsu
2015	J	`jnl`	Mixtures of Local Dictionaries for Unsupervised Speech Enhancement. IEEE Signal Process. Lett. Minje Kim, Paris Smaragdis
2015	—	`conf`	Predicting Skill-Based Task Performance and Learning with fMRI Motor and Subcortical Network Connectivity. PRNI Aki Nikolaidis, Drew Goatz, Paris Smaragdis, Arthur F. Kramer
2014	Misc	`conf`	Deep learning for monaural speech separation. ICASSP Po-Sen Huang, Minje Kim, Mark Hasegawa-Johnson, Paris Smaragdis
2014	—	`conf`	Efficient model selection for speech enhancement using a deflation method for Nonnegative Matrix Factorization. GlobalSIP Minje Kim, Paris Smaragdis
2014	A	`conf`	Experiments on deep learning for speech denoising. INTERSPEECH Ding Liu, Paris Smaragdis, Minje Kim
2014	J	`jnl`	Multichannel source separation and tracking with RANSAC and directional statistics. IEEE ACM Trans. Audio Speech Lang. Process. Johannes Traa, Paris Smaragdis
2014	—	`conf`	Multiple speaker tracking with the Factorial von Mises-Fisher Filter. MLSP Johannes Traa, Paris Smaragdis
2014	Misc	`conf`	Phase and level difference fusion for robust multichannel source separation. ICASSP Johannes Traa, Minje Kim, Paris Smaragdis
2014	—	`conf`	Robust interchannel phase difference modeling with wrapped regression splines. SAM Johannes Traa, Paris Smaragdis
2014	—	`conf`	Singing-Voice Separation from Monaural Recordings using Deep Recurrent Neural Networks. ISMIR Po-Sen Huang, Minje Kim, Mark Hasegawa-Johnson, Paris Smaragdis
2014	—	`conf`	Spectral Learning of Mixture of Hidden Markov Models. NIPS Y. Cem Sübakan, Johannes Traa, Paris Smaragdis
2014	J	`jnl`	Static and Dynamic Source Separation Using Nonnegative Factorizations: A unified view. IEEE Signal Process. Mag. Paris Smaragdis, Cédric Févotte, Gautham J. Mysore, Nasser Mohammadiha, Matthew D. Hoffman
2013	J	`jnl`	A Wrapped Kalman Filter for Azimuthal Speaker Tracking. IEEE Signal Process. Lett. Johannes Traa, Paris Smaragdis
2013	—	`conf`	About this non-negative business. WASPAA Paris Smaragdis
2013	Misc	`conf`	Blind multi-channel source separation by circular-linear statistical modeling of phase differences. ICASSP Johannes Traa, Paris Smaragdis
2013	Misc	`conf`	Collaborative audio enhancement using probabilistic latent component sharing. ICASSP Minje Kim, Paris Smaragdis
2013	B	`conf`	EMERALD: Characterization of emerging applications and algorithms for low-power devices. ISPASS Chuanjun Zhang, Glenn G. Ko, Jungwook Choi, Shang-nien Tsai, Minje Kim, Abner Guzmán-Rivera, Rob A. Rutenbar, Paris Smaragdis, Mi Sun Park, Vijaykrishnan Narayanan, Hongyi Xin, Onur Mutlu, Bin Li, Li Zhao, Mei Chen
2013	—	`conf`	Keynote addresses: From auditory masking to binary classification: Machine learning for speech separation. WASPAA DeLiang Wang, Rainer Martin, Peter Vary, Paris Smaragdis
2013	—	`conf`	Low-artifact source separation using probabilistic latent component analysis. WASPAA Nasser Mohammadiha, Paris Smaragdis, Arne Leijon
2013	—	`conf`	Manifold Preserving Hierarchical Topic Models for Quantization and Approximation. ICML (3) Minje Kim, Paris Smaragdis
2013	—	`conf`	Non-negative matrix factorization for irregularly-spaced transforms. WASPAA Paris Smaragdis, Minje Kim
2013	Misc	`conf`	Prediction based filtering and smoothing to exploit temporal dependencies in NMF. ICASSP Nasser Mohammadiha, Paris Smaragdis, Arne Leijon
2013	J	`jnl`	Privacy-Preserving Speech Processing: Cryptographic and String-Matching Frameworks Show Promise. IEEE Signal Process. Mag. Manas A. Pathak, Bhiksha Raj, Shantanu Rane, Paris Smaragdis
2013	—	`conf`	Simultaneous noise classification and reduction using a priori learned models. MLSP Nasser Mohammadiha, Paris Smaragdis, Arne Leijon
2013	—	`conf`	Single channel source separation using smooth Nonnegative Matrix Factorization with Markov Random Fields. MLSP Minje Kim, Paris Smaragdis
2013	J	`jnl`	Supervised and Unsupervised Speech Enhancement Using Nonnegative Matrix Factorization. IEEE Trans. Speech Audio Process. Nasser Mohammadiha, Paris Smaragdis, Arne Leijon
2012	—	`conf`	A Non-negative Approach to Language Informed Speech Separation. LVA/ICA Gautham J. Mysore, Paris Smaragdis
2012	—	`conf`	An amplitude spectral Capon estimator with a variable filter length. EUSIPCO Jesper Kjær Nielsen, Paris Smaragdis, Mads Græsbøll Christensen, Søren Holdt Jensen
2012	Misc	`conf`	Clustering and synchronizing multi-camera video via landmark cross-correlation. ICASSP Nicholas J. Bryan, Paris Smaragdis, Gautham J. Mysore
2012	—	`ch.`	Extraction of Speech from Mixture Signals. Techniques for Noise Robustness in Automatic Speech Recognition Paris Smaragdis
2012	Misc	`conf`	Following musical sources by example. ICASSP Paris Smaragdis, Gautham J. Mysore
2012	Misc	`conf`	Noise-robust dynamic time warping using PLCA features. ICASSP Brian King, Paris Smaragdis, Gautham J. Mysore
2012	—	`conf`	Online PLCA for Real-Time Semi-supervised Source Separation. LVA/ICA Zhiyao Duan, Gautham J. Mysore, Paris Smaragdis
2012	—	`conf`	Optimal cost function and magnitude power for NMF-based speech separation and music interpolation. MLSP Brian King, Cédric Févotte, Paris Smaragdis
2012	—	`conf`	Second Fiddle is Important Too: Pitch Tracking Individual Voices in Polyphonic Music. ISMIR Mert Bay, Andreas F. Ehmann, James W. Beauchamp, Paris Smaragdis, J. Stephen Downie
2012	Misc	`conf`	Singing-voice separation from monaural recordings using robust principal component analysis. ICASSP Po-Sen Huang, Scott Deeann Chen, Paris Smaragdis, Mark Hasegawa-Johnson
2012	—	`conf`	Sound Recognition in Mixtures. LVA/ICA Juhan Nam, Gautham J. Mysore, Paris Smaragdis
2012	A	`conf`	Speech Enhancement by Online Non-negative Spectrogram Decomposition in Non-stationary Noise Environments. INTERSPEECH Zhiyao Duan, Gautham J. Mysore, Paris Smaragdis
2012	—	`conf`	Stereophonic spectrogram segmentation using Markov random fields. MLSP Minje Kim, Paris Smaragdis, Glenn G. Ko, Rob A. Rutenbar
2012	J	`jnl`	The Markov selection model for concurrent speech recognition. Neurocomputing Paris Smaragdis, Bhiksha Raj
2011	—	`conf`	A convolutive spectral decomposition approach to the separation of feedback from target speech. MLSP Gautham J. Mysore, Paris Smaragdis
2011	Misc	`conf`	A non-negative approach to semi-supervised separation of speech from noise with the use of temporal dynamics. ICASSP Gautham J. Mysore, Paris Smaragdis
2011	Misc	`conf`	An adaptive time-frequency resolution approach for Non-negative Matrix Factorization based single channel sound source separation. ICASSP Serap Kirbiz, Paris Smaragdis
2011	Misc	`conf`	Approximate nearest-subspace representations for sound mixtures. ICASSP Paris Smaragdis
2011	J	`jnl`	Missing Data Imputation for Time-Frequency Representations of Audio Signals. J. Signal Process. Syst. Paris Smaragdis, Bhiksha Raj, Madhusudana V. S. Shashanka
2011	—	`conf`	Polyphonic pitch tracking by example. WASPAA Paris Smaragdis
2011	J	`jnl`	Preface. Speech Commun. Martin Heckmann, Bhiksha Raj, Paris Smaragdis
2010	J	`jnl`	Editorial for the Special Issue on Signal Models and Representations of Musical and Environmental Sounds. IEEE Trans. Speech Audio Process. Bertrand David, Masataka Goto, Laurent Daudet, Paris Smaragdis
2010	Misc	`conf`	Latent-variable decomposition based dereverberation of monaural and multi-channel signals. ICASSP Rita Singh, Bhiksha Raj, Paris Smaragdis
2010	—	`conf`	Non-negative Hidden Markov Modeling of Audio with Application to Source Separation. LVA/ICA Gautham J. Mysore, Paris Smaragdis, Bhiksha Raj
2010	J	`jnl`	Scalable Audio-Content Analysis. EURASIP J. Audio Speech Music. Process. Bhiksha Raj, Paris Smaragdis, Malcolm Slaney, Chung-Hsien Wu, Liming Chen, Hyoung-Gook Kim
2009	—	`conf`	A Sparse Non-Parametric Approach for Single Channel Separation of Known Sounds. NIPS Paris Smaragdis, Madhusudana V. S. Shashanka, Bhiksha Raj
2009	J	`jnl`	Dynamic Range Extension Using Interleaved Gains. IEEE Trans. Speech Audio Process. Paris Smaragdis
2009	—	`conf`	Probabilistic Factorization of Non-negative Data with Entropic Co-occurrence Constraints. ICA Paris Smaragdis, Madhusudana V. S. Shashanka, Bhiksha Raj, Gautham J. Mysore
2009	Misc	`conf`	Relative pitch estimation of multiple instruments. ICASSP Gautham J. Mysore, Paris Smaragdis
2009	—	`conf`	Separation by "humming": User-guided sound extraction from monophonic mixtures. WASPAA Paris Smaragdis, Gautham J. Mysore
2009	—	`conf`	The UBS Virtual Maestro: an Interactive Conducting System. NIME Teresa Marrin Nakra, Yuri Ivanov, Paris Smaragdis, Christopher Ault
2009	A*	`conf`	User guided audio selection from complex sound mixtures. UIST Paris Smaragdis
2008	J	`jnl`	Advances in Nonnegative Matrix and Tensor Factorization. Comput. Intell. Neurosci. Andrzej Cichocki, Morten Mørup, Paris Smaragdis, Wenwu Wang, Rafal Zdunek
2008	J	`jnl`	Probabilistic Latent Variable Models as Nonnegative Factorizations. Comput. Intell. Neurosci. Madhusudana V. S. Shashanka, Bhiksha Raj, Paris Smaragdis
2008	A	`conf`	Regularized non-negative matrix factorization with temporal dependencies for speech denoising. INTERSPEECH Kevin W. Wilson, Bhiksha Raj, Paris Smaragdis
2008	Misc	`conf`	Sparse and shift-invariant feature extraction from non-negative data. ICASSP Paris Smaragdis, Bhiksha Raj, Madhusudana V. S. Shashanka
2008	Misc	`conf`	Speech denoising using nonnegative matrix factorization with priors. ICASSP Kevin W. Wilson, Bhiksha Raj, Paris Smaragdis, Ajay Divakaran
2007	—	`conf`	A Framework for Secure Speech Recognition. ICASSP (4) Paris Smaragdis, Madhusudana V. S. Shashanka
2007	J	`jnl`	A Framework for Secure Speech Recognition. IEEE Trans. Speech Audio Process. Paris Smaragdis, Madhusudana V. S. Shashanka
2007	—	`conf`	Bandwidth Expansionwith a pólya URN Model. ICASSP (4) Bhiksha Raj, Rita Singh, Madhusudana V. S. Shashanka, Paris Smaragdis
2007	J	`jnl`	Convolutive Speech Bases and Their Application to Supervised Speech Separation. IEEE Trans. Speech Audio Process. Paris Smaragdis
2007	J	`jnl`	Position and Trajectory Learning for Microphone Arrays. IEEE Trans. Speech Audio Process. Paris Smaragdis, Petros Boufounos
2007	—	`ch.`	Probabilistic Decompositions of Spectra for Sound Separation. Blind Speech Separation Paris Smaragdis
2007	A*	`conf`	Sensor and Data Systems, Audio-Assisted Cameras and Acoustic Doppler Sensors. CVPR Kaustubh Kalgaonkar, Paris Smaragdis, Bhiksha Raj
2007	—	`conf`	Sparse Overcomplete Decomposition for Single Channel Speaker Separation. ICASSP (2) Madhusudana V. S. Shashanka, Bhiksha Raj, Paris Smaragdis
2007	—	`conf`	Sparse Overcomplete Latent Variable Decomposition of Counts Data. NIPS Madhusudana V. S. Shashanka, Bhiksha Raj, Paris Smaragdis
2007	—	`conf`	Supervised and Semi-supervised Separation of Sounds from Single-Channel Mixtures. ICA Paris Smaragdis, Bhiksha Raj, Madhusudana V. S. Shashanka
2006	—	`conf`	Latent Dirichlet Decomposition for Single Channel Speaker Separation. ICASSP (5) Bhiksha Raj, Madhusudana V. S. Shashanka, Paris Smaragdis
2006	—	`conf`	Secure Sound Classification: Gaussian Mixture Models. ICASSP (3) Madhusudana V. S. Shashanka, Paris Smaragdis
2005	A	`conf`	Bandwidth expansion of narrowband speech using non-negative matrix factorization. INTERSPEECH Dhananjay Bansal, Bhiksha Raj, Paris Smaragdis
2005	—	`ch.`	Exploiting Redundancy to Construct Listening Systems. Speech Separation by Humans and Machines Paris Smaragdis
2005	A	`conf`	Recognizing speech from simultaneous speakers. INTERSPEECH Bhiksha Raj, Rita Singh, Paris Smaragdis
2004	—	`conf`	Discovering auditory objects through non-negativity constraints. SAPA@INTERSPEECH Paris Smaragdis
2004	—	`conf`	Non-negative Matrix Factor Deconvolution; Extraction of Multiple Sound Sources from Monophonic Inputs. ICA Paris Smaragdis
2002	—	`conf`	Combining Musical and Cultural Features for Intelligent Style Detection. ISMIR Brian Whitman, Paris Smaragdis
2000	—	`conf`	Scanned Synthesis: An Introduction and Demonstration of a New Synthesis and Signal Processing Technique. ICMC Richard Boulanger, Paris Smaragdis, John ffitch
1998	J	`jnl`	Blind separation of convolved mixtures in the frequency domain. Neurocomputing Paris Smaragdis
1996	—	`conf`	NetSound: Realtime Audio from Semantic Descriptions. ICMC Michael A. Casey, Paris Smaragdis