default search action
Google
Google Scholar
Semantic Scholar
Internet Archive Scholar
CiteSeerX
ORCIDParis Smaragdis
Person information
- affiliation: MIT, Cambridge, USA
Refine list
refinements active!
zoomed in on ?? of ?? records
view refined list in
export refined list as
showing all ?? records
2020 – today
- 2024
[c116]Jonah Casebeer, Junkai Wu, Paris Smaragdis:
Meta-AF Echo Cancellation for Improved Keyword Spotting. ICASSP 2024: 676-680- [c115]Karim Helwani, Masahito Togami, Paris Smaragdis, Michael M. Goodwin:
Sound Source Separation Using Latent Variational Block-Wise Disentanglement. ICASSP Workshops 2024: 750-754 - [c114]Krishna Subramani, Jean-Marc Valin, Jan Büthe, Paris Smaragdis, Mike Goodwin:
Noise-Robust DSP-Assisted Neural Pitch Estimation With Very Low Complexity. ICASSP 2024: 11851-11855 - [i57]Karim Helwani, Masahito Togami, Paris Smaragdis, Michael M. Goodwin:
Sound Source Separation Using Latent Variational Block-Wise Disentanglement. CoRR abs/2402.06683 (2024) - [i56]Jonah Casebeer, Nicholas J. Bryan, Paris Smaragdis:
Scaling Up Adaptive Filter Optimizers. CoRR abs/2403.00977 (2024) - [i55]Krishna Subramani, Paris Smaragdis, Takuya Higuchi, Mehrez Souden:
Rethinking Non-Negative Matrix Factorization with Implicit Neural Representations. CoRR abs/2404.04439 (2024) - [i54]Tiago Tavares, Fábio Ayres, Zhepei Wang, Paris Smaragdis:
On Class Separability Pitfalls In Audio-Text Contrastive Zero-Shot Learning. CoRR abs/2408.13068 (2024) - 2023
- [j28]Gaël Richard
, Paris Smaragdis, Sharon Gannot, Patrick A. Naylor, Shoji Makino, Walter Kellermann, Akihiko Sugiyama:
Audio Signal Processing in the 21st Century: The important outcomes of the past 25 years. IEEE Signal Process. Mag. 40(5): 12-26 (2023) - [j27]Jonah Casebeer, Nicholas J. Bryan, Paris Smaragdis:
Meta-AF: Meta-Learning for Adaptive Filters. IEEE ACM Trans. Audio Speech Lang. Process. 31: 355-370 (2023) - [c113]Dimitrios Bralios, Efthymios Tzinis, Gordon Wichern, Paris Smaragdis, Jonathan Le Roux:
Latent Iterative Refinement for Modular Source Separation. ICASSP 2023: 1-5 - [c112]Karim Helwani, Paris Smaragdis, Michael M. Goodwin:
Generative Modeling Based Manifold Learning for Adaptive Filtering Guidance. ICASSP 2023: 1-5 - [c111]Ahmed Mustafa, Jean-Marc Valin, Jan Büthe, Paris Smaragdis, Mike Goodwin:
Framewise Wavegan: High Speed Adversarial Vocoder In Time Domain With Very Low Computational Complexity. ICASSP 2023: 1-5 - [c110]Efthymios Tzinis, Gordon Wichern, Paris Smaragdis, Jonathan Le Roux:
Optimal Condition Training for Target Source Separation. ICASSP 2023: 1-5 - [c109]Zhepei Wang, Ritwik Giri, Devansh Shah, Jean-Marc Valin, Michael M. Goodwin, Paris Smaragdis:
A Framework for Unified Real-Time Personalized and Non-Personalized Speech Enhancement. ICASSP 2023: 1-5 - [c108]Erfan Soltanmohammadi, Paris Smaragdis, Michael M. Goodwin:
Low-Complexity Streaming Speech Super-Resolution. MLSP 2023: 1-6 - [c107]Dimitrios Bralios, Efthymios Tzinis, Paris Smaragdis:
Complete and Separate: Conditional Separation with Missing Target Source Attribute Completion. WASPAA 2023: 1-5 - [c106]Zhepei Wang, Cem Subakan, Krishna Subramani, Junkai Wu, Tiago Tavares, Fábio Ayres, Paris Smaragdis:
Unsupervised Improvement of Audio-Text Cross-Modal Representations. WASPAA 2023: 1-5 - [i53]Zhepei Wang, Ritwik Giri, Devansh Shah, Jean-Marc Valin, Michael M. Goodwin, Paris Smaragdis:
A Framework for Unified Real-time Personalized and Non-Personalized Speech Enhancement. CoRR abs/2302.11768 (2023) - [i52]Zhepei Wang, Cem Subakan, Krishna Subramani, Junkai Wu, Tiago Tavares, Fábio Ayres, Paris Smaragdis:
Unsupervised Improvement of Audio-Text Cross-Modal Representations. CoRR abs/2305.01864 (2023) - [i51]Dimitrios Bralios, Efthymios Tzinis, Paris Smaragdis:
Complete and separate: Conditional separation with missing target source attribute completion. CoRR abs/2307.14609 (2023) - [i50]Krishna Subramani, Jean-Marc Valin, Jan Büthe, Paris Smaragdis, Mike Goodwin:
Noise-Robust DSP-Assisted Neural Pitch Estimation with Very Low Complexity. CoRR abs/2309.14507 (2023) - [i49]Austin Lu, Ethaniel Moore, Arya Nallanthighall, Kanad Sarkar, Manan Mittal, Ryan M. Corey, Paris Smaragdis, Andrew C. Singer:
Mechatronic Generation of Datasets for Acoustics Research. CoRR abs/2310.00587 (2023) - [i48]Francesco Paissan, Zhepei Wang, Mirco Ravanelli, Paris Smaragdis, Cem Subakan:
Audio Editing with Non-Rigid Text Prompts. CoRR abs/2310.12858 (2023) - [i47]Jonah Casebeer, Junkai Wu, Paris Smaragdis:
Meta-AF Echo Cancellation for Improved Keyword Spotting. CoRR abs/2312.10605 (2023) - 2022
- [j26]Efthymios Tzinis, Yossi Adi, Vamsi K. Ithapu, Buye Xu, Paris Smaragdis, Anurag Kumar:
RemixIT: Continual Self-Training of Speech Enhancement Models via Bootstrapped Remixing. IEEE J. Sel. Top. Signal Process. 16(6): 1329-1341 (2022) - [j25]Zhepei Wang, Cem Subakan, Xilin Jiang, Junkai Wu, Efthymios Tzinis, Mirco Ravanelli, Paris Smaragdis:
Learning Representations for New Sound Classes With Continual Self-Supervised Learning. IEEE Signal Process. Lett. 29: 2607-2611 (2022) - [j24]Efthymios Tzinis, Zhepei Wang, Xilin Jiang, Paris Smaragdis:
Compute and Memory Efficient Universal Sound Source Separation. J. Signal Process. Syst. 94(2): 245-259 (2022) - [c105]Jean-Marc Valin, Umut Isik, Paris Smaragdis, Arvindh Krishnaswamy:
Neural Speech Synthesis on a Shoestring: Improving the Efficiency of Lpcnet. ICASSP 2022: 8437-8441 - [c104]Jean-Marc Valin, Ahmed Mustafa, Christopher Montgomery, Timothy B. Terriberry, Michael Klingbeil, Paris Smaragdis, Arvindh Krishnaswamy:
Real-Time Packet Loss Concealment With Mixed Generative and Predictive Model. INTERSPEECH 2022: 570-574 - [c103]Krishna Subramani, Jean-Marc Valin, Umut Isik, Paris Smaragdis, Arvindh Krishnaswamy:
End-to-end LPCNet: A Neural Vocoder With Fully-Differentiable LPC Estimation. INTERSPEECH 2022: 818-822 - [c102]Efthymios Tzinis, Gordon Wichern, Aswin Shanmugam Subramanian, Paris Smaragdis, Jonathan Le Roux:
Heterogeneous Target Speech Separation. INTERSPEECH 2022: 1796-1800 - [c101]Austin Lu, Ethaniel Moore, Arya Nallanthighall, Kanad Sarkar, Manan Mittal, Ryan M. Corey, Paris Smaragdis, Andrew C. Singer:
Mechatronic Generation of Datasets for Acoustics Research. IWAENC 2022: 1-5 - [c100]Junkai Wu, Jonah Casebeer, Nicholas J. Bryan, Paris Smaragdis:
Meta-Learning for Adaptive Filters with higher-order Frequency Dependencies. IWAENC 2022: 1-5 - [i46]Efthymios Tzinis, Yossi Adi, Vamsi Krishna Ithapu, Buye Xu, Paris Smaragdis, Anurag Kumar:
RemixIT: Continual self-training of speech enhancement models via bootstrapped remixing. CoRR abs/2202.08862 (2022) - [i45]Jean-Marc Valin, Umut Isik, Paris Smaragdis, Arvindh Krishnaswamy:
Neural Speech Synthesis on a Shoestring: Improving the Efficiency of LPCNet. CoRR abs/2202.11169 (2022) - [i44]Krishna Subramani, Jean-Marc Valin, Umut Isik, Paris Smaragdis, Arvindh Krishnaswamy:
End-to-end LPCNet: A Neural Vocoder With Fully-Differentiable LPC Estimation. CoRR abs/2202.11301 (2022) - [i43]Efthymios Tzinis, Gordon Wichern, Aswin Shanmugam Subramanian, Paris Smaragdis, Jonathan Le Roux:
Heterogeneous Target Speech Separation. CoRR abs/2204.03594 (2022) - [i42]Jonah Casebeer, Nicholas J. Bryan, Paris Smaragdis:
Meta-AF: Meta-Learning for Adaptive Filters. CoRR abs/2204.11942 (2022) - [i41]Jean-Marc Valin, Ahmed Mustafa, Christopher Montgomery, Timothy B. Terriberry, Michael Klingbeil, Paris Smaragdis, Arvindh Krishnaswamy:
Real-Time Packet Loss Concealment With Mixed Generative and Predictive Model. CoRR abs/2205.05785 (2022) - [i40]Zhepei Wang, Cem Subakan, Xilin Jiang, Junkai Wu, Efthymios Tzinis, Mirco Ravanelli, Paris Smaragdis:
Learning Representations for New Sound Classes With Continual Self-Supervised Learning. CoRR abs/2205.07390 (2022) - [i39]Zhepei Wang, Ritwik Giri, Shrikant Venkataramani, Umut Isik, Jean-Marc Valin, Paris Smaragdis, Michael M. Goodwin, Arvindh Krishnaswamy:
Semi-supervised Time Domain Target Speaker Extraction with Attention. CoRR abs/2206.09072 (2022) - [i38]Anku Adhikari, Samuel Guo, Paris Smaragdis, Marianne Winslett:
Don't Look Up: Ubiquitous Data Exfiltration Pathways in Commercial Spaces. CoRR abs/2206.12944 (2022) - [i37]Junkai Wu, Jonah Casebeer, Nicholas J. Bryan, Paris Smaragdis:
Meta-Learning for Adaptive Filters with Higher-Order Frequency Dependencies. CoRR abs/2209.09955 (2022) - [i36]Efthymios Tzinis, Gordon Wichern, Paris Smaragdis, Jonathan Le Roux:
Optimal Condition Training for Target Source Separation. CoRR abs/2211.05927 (2022) - [i35]Dimitrios Bralios, Efthymios Tzinis, Gordon Wichern, Paris Smaragdis, Jonathan Le Roux:
Latent Iterative Refinement for Modular Source Separation. CoRR abs/2211.11917 (2022) - [i34]Ahmed Mustafa, Jean-Marc Valin, Jan Büthe, Paris Smaragdis, Mike Goodwin:
Framewise WaveGAN: High Speed Adversarial Vocoder in Time Domain with Very Low Computational Complexity. CoRR abs/2212.04532 (2022) - 2021
- [c99]Marco A. Martínez Ramírez, Oliver Wang, Paris Smaragdis, Nicholas J. Bryan:
Differentiable Signal Processing With Black-Box Audio Effects. ICASSP 2021: 66-70 - [c98]Efthymios Tzinis, Dimitrios Bralios, Paris Smaragdis:
Unified Gradient Reweighting for Model Biasing with Applications to Source Separation. ICASSP 2021: 531-535 - [c97]An Zhao, Krishna Subramani, Paris Smaragdis:
Optimizing Short-Time Fourier Transform Parameters via Gradient Descent. ICASSP 2021: 736-740 - [c96]Jonah Casebeer, Jamshed Kaikaus, Paris Smaragdis:
Communication-Cost Aware Microphone Selection for Neural Speech Enhancement with Ad-Hoc Microphone Arrays. ICASSP 2021: 8438-8442 - [c95]Krishna Subramani, Paris Smaragdis:
Point Cloud Audio Processing. WASPAA 2021: 31-35 - [c94]Zhepei Wang, Jonah Casebeer, Adam Clemmitt, Efthymios Tzinis, Paris Smaragdis:
Sound Event Detection with Adaptive Frequency Selection. WASPAA 2021: 41-45 - [c93]Efthymios Tzinis, Jonah Casebeer, Zhepei Wang, Paris Smaragdis:
Separate But Together: Unsupervised Federated Learning for Speech Enhancement from Non-IID Data. WASPAA 2021: 46-50 - [c92]Jonah Casebeer, Nicholas J. Bryan, Paris Smaragdis:
Auto-DSP: Learning to Optimize Acoustic Echo Cancellers. WASPAA 2021: 291-295 - [i33]Efthymios Tzinis, Zhepei Wang, Xilin Jiang, Paris Smaragdis:
Compute and memory efficient universal sound source separation. CoRR abs/2103.02644 (2021) - [i32]Krishna Subramani, Paris Smaragdis:
Point Cloud Audio Processing. CoRR abs/2105.02469 (2021) - [i31]Efthymios Tzinis, Jonah Casebeer, Zhepei Wang, Paris Smaragdis:
Separate but Together: Unsupervised Federated Learning for Speech Enhancement from Non-IID Data. CoRR abs/2105.04727 (2021) - [i30]Marco A. Martínez Ramírez, Oliver Wang, Paris Smaragdis, Nicholas J. Bryan:
Differentiable Signal Processing With Black-Box Audio Effects. CoRR abs/2105.04752 (2021) - [i29]Zhepei Wang, Jonah Casebeer, Adam Clemmitt, Efthymios Tzinis, Paris Smaragdis:
Sound Event Detection with Adaptive Frequency Selection. CoRR abs/2105.07596 (2021) - [i28]Jonah Casebeer, Nicholas J. Bryan, Paris Smaragdis:
Auto-DSP: Learning to Optimize Acoustic Echo Cancellers. CoRR abs/2110.04284 (2021) - 2020
- [c91]Efthymios Tzinis, Shrikant Venkataramani, Zhepei Wang, Y. Cem Sübakan, Paris Smaragdis:
Two-Step Sound Source Separation: Training On Learned Latent Targets. ICASSP 2020: 31-35 - [c90]Shrikant Venkataramani, Efthymios Tzinis, Paris Smaragdis:
End-To-End Non-Negative Autoencoders for Sound Source Separation. ICASSP 2020: 116-120 - [c89]Stylianos I. Mimilakis, Nicholas J. Bryan, Paris Smaragdis:
One-Shot Parametric Audio Production Style Transfer with Application to Frequency Equalization. ICASSP 2020: 256-260 - [c88]Efthymios Tzinis, Zhepei Wang, Paris Smaragdis:
Sudo RM -RF: Efficient Networks for Universal Audio Source Separation. MLSP 2020: 1-6 - [i27]Yu-Che Wang, Shrikant Venkataramani, Paris Smaragdis:
Self-supervised Learning for Speech Enhancement. CoRR abs/2006.10388 (2020) - [i26]Efthymios Tzinis, Zhepei Wang, Paris Smaragdis:
Sudo rm -rf: Efficient Networks for Universal Audio Source Separation. CoRR abs/2007.06833 (2020) - [i25]Efthymios Tzinis, Dimitrios Bralios, Paris Smaragdis:
Unified Gradient Reweighting for Model Biasing with Applications to Source Separation. CoRR abs/2010.13228 (2020) - [i24]An Zhao, Krishna Subramani, Paris Smaragdis:
Optimizing Short-Time Fourier Transform Parameters via Gradient Descent. CoRR abs/2010.15049 (2020) - [i23]Jonah Casebeer, Jamshed Kaikaus, Paris Smaragdis:
Communication-Cost Aware Microphone Selection For Neural Speech Enhancement with Ad-hoc Microphone Arrays. CoRR abs/2011.07348 (2020)
2010 – 2019
- 2019
- [c87]Prem Seetharaman, Gautham J. Mysore, Bryan Pardo, Paris Smaragdis, Celso Gomes:
VoiceAssist: Guiding Users to High-Quality Voice Recordings. CHI 2019: 309 - [c86]Efthymios Tzinis, Shrikant Venkataramani, Paris Smaragdis:
Unsupervised Deep Clustering for Source Separation: Direct Learning from Mixtures Using Spatial Information. ICASSP 2019: 81-85 - [c85]Jonah Casebeer, Zhepei Wang, Paris Smaragdis:
Multi-view Networks for Multi-channel Audio Classification. ICASSP 2019: 940-944 - [c84]Dylan Fagot, Herwig Wendt, Cédric Févotte, Paris Smaragdis:
Majorization-minimization Algorithms for Convolutive NMF with the Beta-divergence. ICASSP 2019: 8202-8206 - [c83]Shrikant Venkataramani, Efthymios Tzinis, Paris Smaragdis:
A Style Transfer Approach to Source Separation. WASPAA 2019: 170-174 - [c82]Jonah Casebeer, Michael Colomb, Paris Smaragdis:
Deep Tensor Factorization for Spatially-Aware Scene Decomposition. WASPAA 2019: 180-184 - [c81]Zhepei Wang, Y. Cem Sübakan, Efthymios Tzinis, Paris Smaragdis, Laurent Charlin:
Continual Learning of New Sound Classes Using Generative Replay. WASPAA 2019: 308-312 - [i22]Shrikant Venkataramani, Efthymios Tzinis, Paris Smaragdis:
A Style Transfer Approach to Source Separation. CoRR abs/1905.00151 (2019) - [i21]Jonah Casebeer, Michael Colomb, Paris Smaragdis:
Deep Tensor Factorization for Spatially-Aware Scene Decomposition. CoRR abs/1905.01391 (2019) - [i20]Zhepei Wang, Y. Cem Sübakan, Efthymios Tzinis, Paris Smaragdis, Laurent Charlin:
Continual Learning of New Sound Classes using Generative Replay. CoRR abs/1906.00654 (2019) - [i19]Efthymios Tzinis, Shrikant Venkataramani, Zhepei Wang, Y. Cem Sübakan, Paris Smaragdis:
Two-Step Sound Source Separation: Training on Learned Latent Targets. CoRR abs/1910.09804 (2019) - [i18]Shrikant Venkataramani, Efthymios Tzinis, Paris Smaragdis:
End-to-end Non-Negative Autoencoders for Sound Source Separation. CoRR abs/1911.00102 (2019) - 2018
- [c80]Shrikant Venkataramani, Jonah Casebeer, Paris Smaragdis:
End-To-End Source Separation With Adaptive Front-Ends. ACSSC 2018: 684-688 - [c79]Shrikant Venkataramani, Ryley Higa, Paris Smaragdis:
Performance Based Cost Functions for End-to-End Speech Separation. APSIPA 2018: 350-355 - [c78]Y. Cem Sübakan, Paris Smaragdis:
Generative Adversarial Source Separation. ICASSP 2018: 26-30 - [c77]Prem Seetharaman, Gautham J. Mysore, Paris Smaragdis, Bryan Pardo:
Blind Estimation of the Speech Transmission Index for Speech Quality Prediction. ICASSP 2018: 591-595 - [c76]Minje Kim, Paris Smaragdis:
Bitwise Neural Networks for Efficient Single-Channel Source Separation. ICASSP 2018: 701-705 - [c75]Jonah Casebeer, Brian Luc, Paris Smaragdis:
Multi-View Networks for Denoising of Arbitrary Numbers of Channels. IWAENC 2018: 496-500 - [p4]Gerald Friedland, Paris Smaragdis, Josh H. McDermott, Bhiksha Raj:
Audition for multimedia computing. Frontiers of Multimedia Research 2018: 31-50 - [i17]Y. Cem Sübakan, Oluwasanmi Koyejo, Paris Smaragdis:
Learning the Base Distribution in Implicit Generative Models. CoRR abs/1803.04357 (2018) - [i16]Shrikant Venkataramani, Ryley Higa, Paris Smaragdis:
Performance Based Cost Functions for End-to-End Speech Separation. CoRR abs/1806.00511 (2018) - [i15]Jonah Casebeer, Brian Luc, Paris Smaragdis:
Multi-View Networks for Denoising of Arbitrary Numbers of Channels. CoRR abs/1806.05296 (2018) - [i14]Shrikant Venkataramani, Paris Smaragdis:
End-to-end Networks for Supervised Single-channel Speech Separation. CoRR abs/1810.02568 (2018) - [i13]Jonah Casebeer, Zhepei Wang, Paris Smaragdis:
Multi-View Networks For Multi-Channel Audio Classification. CoRR abs/1811.01251 (2018) - [i12]Efthymios Tzinis, Shrikant Venkataramani, Paris Smaragdis:
Unsupervised Deep Clustering for Source Separation: Direct Learning from Mixtures using Spatial Information. CoRR abs/1811.01531 (2018) - 2017
- [c74]Paris Smaragdis, Shrikant Venkataramani:
A neural network alternative to non-negative audio models. ICASSP 2017: 86-90 - [c73]Shrikant Venkataramani, Y. Cem Sübakan, Paris Smaragdis:
Neural network alternatives toconvolutive audio models for source separation. MLSP 2017: 1-6 - [c72]Shrikant Venkataramani, Paris Smaragdis, Gautham J. Mysore:
AutoDub: Automatic Redubbing for Voiceover Editing. UIST 2017: 533-538 - [c71]Ralf Gunter Correa Carvalho, Paris Smaragdis:
Towards end-to-end polyphonic music transcription: Transforming music audio directly to a score. WASPAA 2017: 151-155 - [c70]Y. Cem Sübakan, Paris Smaragdis:
Diagonal rnns in symbolic music modeling. WASPAA 2017: 354-358 - [i11]Y. Cem Sübakan, Paris Smaragdis:
Diagonal RNNs in Symbolic Music Modeling. CoRR abs/1704.05420 (2017) - [i10]Shrikant Venkataramani, Paris Smaragdis:
End-to-end Source Separation with Adaptive Front-Ends. CoRR abs/1705.02514 (2017) - [i9]Nasser Mohammadiha, Paris Smaragdis, Ghazaleh Panahandeh, Simon Doclo:
A State-Space Approach to Dynamic Nonnegative Matrix Factorization. CoRR abs/1709.00025 (2017) - [i8]Nasser Mohammadiha, Paris Smaragdis, Arne Leijon:
Supervised and Unsupervised Speech Enhancement Using Nonnegative Matrix Factorization. CoRR abs/1709.05362 (2017) - [i7]Shrikant Venkataramani, Y. Cem Sübakan, Paris Smaragdis:
Neural Network Alternatives to Convolutive Audio Models for Source Separation. CoRR abs/1709.07908 (2017) - [i6]Y. Cem Sübakan, Paris Smaragdis:
Generative Adversarial Source Separation. CoRR abs/1710.10779 (2017) - 2016
- [j23]Johannes Traa, David Wingate, Noah D. Stein, Paris Smaragdis:
Robust Source Localization and Enhancement With a Probabilistic Steered Response Power Model. IEEE ACM Trans. Audio Speech Lang. Process. 24(3): 493-503 (2016) - [c69]Minje Kim, Paris Smaragdis:
Efficient neighborhood-based topic modeling for collaborative audio enhancement on massive crowdsourced recordings. ICASSP 2016: 41-45 - [i5]Minje Kim, Paris Smaragdis:
Bitwise Neural Networks. CoRR abs/1601.06071 (2016) - [i4]Paris Smaragdis, Shrikant Venkataramani:
A Neural Network Alternative to Non-Negative Audio Models. CoRR abs/1609.03296 (2016) - [i3]Mohammad Babaeizadeh, Paris Smaragdis, Roy H. Campbell:
NoiseOut: A Simple Way to Prune Neural Networks. CoRR abs/1611.06211 (2016) - 2015
- [j22]Minje Kim, Paris Smaragdis:
Mixtures of Local Dictionaries for Unsupervised Speech Enhancement. IEEE Signal Process. Lett. 22(3): 288-292 (2015) - [j21]Tuomas Virtanen, Jort Florent Gemmeke, Bhiksha Raj, Paris Smaragdis:
Compositional Models for Audio Processing: Uncovering the structure of sound mixtures. IEEE Signal Process. Mag. 32(2): 125-144 (2015) - [j20]Po-Sen Huang, Minje Kim, Mark Hasegawa-Johnson, Paris Smaragdis:
Joint Optimization of Masks and Deep Recurrent Neural Networks for Monaural Source Separation. IEEE ACM Trans. Audio Speech Lang. Process. 23(12): 2136-2147 (2015) - [j19]Nasser Mohammadiha, Paris Smaragdis, Ghazaleh Panahandeh, Simon Doclo:
A State-Space Approach to Dynamic Nonnegative Matrix Factorization. IEEE Trans. Signal Process. 63(4): 949-959 (2015) - [j18]Saeid Sanei, Paris Smaragdis, Anthony T. S. Ho, Asoke K. Nandi, Jan Larsen:
Guest Editorial: Machine Learning for Signal Processing. J. Signal Process. Syst. 79(2): 113-116 (2015) - [c68]Minje Kim, Paris Smaragdis:
Adaptive Denoising Autoencoders: A Fine-Tuning Scheme to Learn from Test Mixtures. LVA/ICA 2015: 100-107 - [c67]Minje Kim, Paris Smaragdis, Gautham J. Mysore:
Efficient manifold preserving audio source separation using locality sensitive hashing. ICASSP 2015: 479-483 - [c66]Nasser Mohammadiha, Paris Smaragdis, Simon Doclo:
Joint acoustic and spectral modeling for speech dereverberation using non-negative representations. ICASSP 2015: 4410-4414 - [c65]Aki Nikolaidis, Drew Goatz, Paris Smaragdis, Arthur F. Kramer:
Predicting Skill-Based Task Performance and Learning with fMRI Motor and Subcortical Network Connectivity. PRNI 2015: 93-96 - [c64]Y. Cem Sübakan, Johannes Traa, Paris Smaragdis, Daniel J. Hsu:
Method of moments learning for left-to-right Hidden Markov models. WASPAA 2015: 1-5 - [c63]Johannes Traa, Paris Smaragdis, Noah D. Stein, David Wingate:
Directional NMF for joint source localization and separation. WASPAA 2015: 1-5 - [i2]Po-Sen Huang, Minje Kim, Mark Hasegawa-Johnson, Paris Smaragdis:
Joint Optimization of Masks and Deep Recurrent Neural Networks for Monaural Source Separation. CoRR abs/1502.04149 (2015) - [i1]Y. Cem Sübakan, Johannes Traa, Paris Smaragdis, Noah D. Stein:
A Dictionary Learning Approach for Factorial Gaussian Models. CoRR abs/1508.04486 (2015) - 2014
- [j17]Paris Smaragdis, Cédric Févotte, Gautham J. Mysore, Nasser Mohammadiha, Matthew D. Hoffman:
Static and Dynamic Source Separation Using Nonnegative Factorizations: A unified view. IEEE Signal Process. Mag. 31(3): 66-75 (2014) - [j16]Johannes Traa, Paris Smaragdis:
Multichannel source separation and tracking with RANSAC and directional statistics. IEEE ACM Trans. Audio Speech Lang. Process. 22(12): 2233-2243 (2014) - [c62]Minje Kim, Paris Smaragdis:
Efficient model selection for speech enhancement using a deflation method for Nonnegative Matrix Factorization. GlobalSIP 2014: 537-541 - [c61]Po-Sen Huang, Minje Kim, Mark Hasegawa-Johnson, Paris Smaragdis:
Deep learning for monaural speech separation. ICASSP 2014: 1562-1566 - [c60]Johannes Traa, Minje Kim, Paris Smaragdis:
Phase and level difference fusion for robust multichannel source separation. ICASSP 2014: 6687-6691 - [c59]Johannes Traa, Paris Smaragdis:
Robust interchannel phase difference modeling with wrapped regression splines. SAM 2014: 69-72 - [c58]Ding Liu, Paris Smaragdis, Minje Kim:
Experiments on deep learning for speech denoising. INTERSPEECH 2014: 2685-2689 - [c57]Po-Sen Huang, Minje Kim, Mark Hasegawa-Johnson, Paris Smaragdis:
Singing-Voice Separation from Monaural Recordings using Deep Recurrent Neural Networks. ISMIR 2014: 477-482 - [c56]Johannes Traa, Paris Smaragdis:
Multiple speaker tracking with the Factorial von Mises-Fisher Filter. MLSP 2014: 1-6 - [c55]Y. Cem Sübakan, Johannes Traa, Paris Smaragdis:
Spectral Learning of Mixture of Hidden Markov Models. NIPS 2014: 2249-2257 - 2013
- [j15]Johannes Traa, Paris Smaragdis:
A Wrapped Kalman Filter for Azimuthal Speaker Tracking. IEEE Signal Process. Lett. 20(12): 1257-1260 (2013) - [j14]Manas A. Pathak, Bhiksha Raj, Shantanu Rane, Paris Smaragdis:
Privacy-Preserving Speech Processing: Cryptographic and String-Matching Frameworks Show Promise. IEEE Signal Process. Mag. 30(2): 62-74 (2013) - [j13]Nasser Mohammadiha, Paris Smaragdis, Arne Leijon:
Supervised and Unsupervised Speech Enhancement Using Nonnegative Matrix Factorization. IEEE Trans. Speech Audio Process. 21(10): 2140-2151 (2013) - [c54]Nasser Mohammadiha, Paris Smaragdis, Arne Leijon:
Prediction based filtering and smoothing to exploit temporal dependencies in NMF. ICASSP 2013: 873-877 - [c53]Minje Kim, Paris Smaragdis:
Collaborative audio enhancement using probabilistic latent component sharing. ICASSP 2013: 896-900 - [c52]Johannes Traa, Paris Smaragdis:
Blind multi-channel source separation by circular-linear statistical modeling of phase differences. ICASSP 2013: 4320-4324 - [c51]Minje Kim, Paris Smaragdis:
Manifold Preserving Hierarchical Topic Models for Quantization and Approximation. ICML (3) 2013: 1373-1381 - [c50]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:
EMERALD: Characterization of emerging applications and algorithms for low-power devices. ISPASS 2013: 122-123 - [c49]Minje Kim, Paris Smaragdis:
Single channel source separation using smooth Nonnegative Matrix Factorization with Markov Random Fields. MLSP 2013: 1-6 - [c48]Nasser Mohammadiha, Paris Smaragdis, Arne Leijon:
Simultaneous noise classification and reduction using a priori learned models. MLSP 2013: 1-6 - [c47]Nasser Mohammadiha, Paris Smaragdis, Arne Leijon:
Low-artifact source separation using probabilistic latent component analysis. WASPAA 2013: 1-4 - [c46]Paris Smaragdis:
About this non-negative business. WASPAA 2013: 1 - [c45]Paris Smaragdis, Minje Kim:
Non-negative matrix factorization for irregularly-spaced transforms. WASPAA 2013: 1-4 - [c44]DeLiang Wang, Rainer Martin, Peter Vary, Paris Smaragdis:
Keynote addresses: From auditory masking to binary classification: Machine learning for speech separation. WASPAA 2013: 1-3 - 2012
- [j12]Paris Smaragdis, Bhiksha Raj:
The Markov selection model for concurrent speech recognition. Neurocomputing 80: 64-72 (2012) - [c43]Jesper Kjær Nielsen, Paris Smaragdis, Mads Græsbøll Christensen, Søren Holdt Jensen:
An amplitude spectral Capon estimator with a variable filter length. EUSIPCO 2012: 430-434 - [c42]Zhiyao Duan, Gautham J. Mysore, Paris Smaragdis:
Online PLCA for Real-Time Semi-supervised Source Separation. LVA/ICA 2012: 34-41 - [c41]Gautham J. Mysore, Paris Smaragdis:
A Non-negative Approach to Language Informed Speech Separation. LVA/ICA 2012: 356-363 - [c40]Juhan Nam, Gautham J. Mysore, Paris Smaragdis:
Sound Recognition in Mixtures. LVA/ICA 2012: 405-413 - [c39]Po-Sen Huang, Scott Deeann Chen, Paris Smaragdis, Mark Hasegawa-Johnson:
Singing-voice separation from monaural recordings using robust principal component analysis. ICASSP 2012: 57-60 - [c38]Brian King, Paris Smaragdis, Gautham J. Mysore:
Noise-robust dynamic time warping using PLCA features. ICASSP 2012: 1973-1976 - [c37]Nicholas J. Bryan, Paris Smaragdis, Gautham J. Mysore:
Clustering and synchronizing multi-camera video via landmark cross-correlation. ICASSP 2012: 2389-2392 - [c36]Paris Smaragdis, Gautham J. Mysore:
Following musical sources by example. ICASSP 2012: 5373-5376 - [c35]Zhiyao Duan, Gautham J. Mysore, Paris Smaragdis:
Speech Enhancement by Online Non-negative Spectrogram Decomposition in Non-stationary Noise Environments. INTERSPEECH 2012: 595-598 - [c34]Mert Bay, Andreas F. Ehmann, James W. Beauchamp, Paris Smaragdis, J. Stephen Downie:
Second Fiddle is Important Too: Pitch Tracking Individual Voices in Polyphonic Music. ISMIR 2012: 319-324 - [c33]Minje Kim, Paris Smaragdis, Glenn G. Ko, Rob A. Rutenbar:
Stereophonic spectrogram segmentation using Markov random fields. MLSP 2012: 1-6 - [c32]Brian King, Cédric Févotte, Paris Smaragdis:
Optimal cost function and magnitude power for NMF-based speech separation and music interpolation. MLSP 2012: 1-6 - [p3]Paris Smaragdis:
Extraction of Speech from Mixture Signals. Techniques for Noise Robustness in Automatic Speech Recognition 2012: 87-108 - 2011
- [j11]Martin Heckmann, Bhiksha Raj, Paris Smaragdis:
Preface. Speech Commun. 53(5): 591 (2011) - [j10]Paris Smaragdis, Bhiksha Raj, Madhusudana V. S. Shashanka:
Missing Data Imputation for Time-Frequency Representations of Audio Signals. J. Signal Process. Syst. 65(3): 361-370 (2011) - [c31]Gautham J. Mysore, Paris Smaragdis:
A non-negative approach to semi-supervised separation of speech from noise with the use of temporal dynamics. ICASSP 2011: 17-20 - [c30]Serap Kirbiz, Paris Smaragdis:
An adaptive time-frequency resolution approach for Non-negative Matrix Factorization based single channel sound source separation. ICASSP 2011: 253-256 - [c29]Paris Smaragdis:
Approximate nearest-subspace representations for sound mixtures. ICASSP 2011: 5892-5895 - [c28]Gautham J. Mysore, Paris Smaragdis:
A convolutive spectral decomposition approach to the separation of feedback from target speech. MLSP 2011: 1-6 - [c27]Paris Smaragdis:
Polyphonic pitch tracking by example. WASPAA 2011: 125-128 - 2010
- [j9]Bhiksha Raj, Paris Smaragdis, Malcolm Slaney, Chung-Hsien Wu, Liming Chen, Hyoung-Gook Kim:
Scalable Audio-Content Analysis. EURASIP J. Audio Speech Music. Process. 2010 (2010) - [j8]Bertrand David, Masataka Goto, Laurent Daudet, Paris Smaragdis:
Editorial for the Special Issue on Signal Models and Representations of Musical and Environmental Sounds. IEEE Trans. Speech Audio Process. 18(3): 417-419 (2010) - [c26]Gautham J. Mysore, Paris Smaragdis, Bhiksha Raj:
Non-negative Hidden Markov Modeling of Audio with Application to Source Separation. LVA/ICA 2010: 140-148 - [c25]Rita Singh, Bhiksha Raj, Paris Smaragdis:
Latent-variable decomposition based dereverberation of monaural and multi-channel signals. ICASSP 2010: 1914-1917
2000 – 2009
- 2009
- [j7]Paris Smaragdis:
Dynamic Range Extension Using Interleaved Gains. IEEE Trans. Speech Audio Process. 17(5): 966-973 (2009) - [c24]Gautham J. Mysore, Paris Smaragdis:
Relative pitch estimation of multiple instruments. ICASSP 2009: 313-316 - [c23]Paris Smaragdis, Madhusudana V. S. Shashanka, Bhiksha Raj, Gautham J. Mysore:
Probabilistic Factorization of Non-negative Data with Entropic Co-occurrence Constraints. ICA 2009: 330-337 - [c22]Teresa Marrin Nakra, Yuri Ivanov, Paris Smaragdis, Christopher Ault:
The UBS Virtual Maestro: an Interactive Conducting System. NIME 2009: 250-255 - [c21]Paris Smaragdis, Madhusudana V. S. Shashanka, Bhiksha Raj:
A Sparse Non-Parametric Approach for Single Channel Separation of Known Sounds. NIPS 2009: 1705-1713 - [c20]Paris Smaragdis:
User guided audio selection from complex sound mixtures. UIST 2009: 89-92 - [c19]Paris Smaragdis, Gautham J. Mysore:
Separation by "humming": User-guided sound extraction from monophonic mixtures. WASPAA 2009: 69-72 - 2008
- [j6]Andrzej Cichocki, Morten Mørup, Paris Smaragdis, Wenwu Wang, Rafal Zdunek:
Advances in Nonnegative Matrix and Tensor Factorization. Comput. Intell. Neurosci. 2008 (2008) - [j5]Madhusudana V. S. Shashanka, Bhiksha Raj, Paris Smaragdis:
Probabilistic Latent Variable Models as Nonnegative Factorizations. Comput. Intell. Neurosci. 2008 (2008) - [c18]Paris Smaragdis, Bhiksha Raj, Madhusudana V. S. Shashanka:
Sparse and shift-invariant feature extraction from non-negative data. ICASSP 2008: 2069-2072 - [c17]Kevin W. Wilson, Bhiksha Raj, Paris Smaragdis, Ajay Divakaran:
Speech denoising using nonnegative matrix factorization with priors. ICASSP 2008: 4029-4032 - [c16]Kevin W. Wilson, Bhiksha Raj, Paris Smaragdis:
Regularized non-negative matrix factorization with temporal dependencies for speech denoising. INTERSPEECH 2008: 411-414 - 2007
- [j4]Paris Smaragdis:
Convolutive Speech Bases and Their Application to Supervised Speech Separation. IEEE Trans. Speech Audio Process. 15(1): 1-12 (2007) - [j3]Paris Smaragdis, Petros Boufounos:
Position and Trajectory Learning for Microphone Arrays. IEEE Trans. Speech Audio Process. 15(1): 358-368 (2007) - [j2]Paris Smaragdis, Madhusudana V. S. Shashanka:
A Framework for Secure Speech Recognition. IEEE Trans. Speech Audio Process. 15(4): 1404-1413 (2007) - [c15]Kaustubh Kalgaonkar, Paris Smaragdis, Bhiksha Raj:
Sensor and Data Systems, Audio-Assisted Cameras and Acoustic Doppler Sensors. CVPR 2007 - [c14]Paris Smaragdis, Bhiksha Raj, Madhusudana V. S. Shashanka:
Supervised and Semi-supervised Separation of Sounds from Single-Channel Mixtures. ICA 2007: 414-421 - [c13]Bhiksha Raj, Rita Singh, Madhusudana V. S. Shashanka, Paris Smaragdis:
Bandwidth Expansionwith a pólya URN Model. ICASSP (4) 2007: 597-600 - [c12]Madhusudana V. S. Shashanka, Bhiksha Raj, Paris Smaragdis:
Sparse Overcomplete Decomposition for Single Channel Speaker Separation. ICASSP (2) 2007: 641-644 - [c11]Paris Smaragdis, Madhusudana V. S. Shashanka:
A Framework for Secure Speech Recognition. ICASSP (4) 2007: 969-972 - [c10]Madhusudana V. S. Shashanka, Bhiksha Raj, Paris Smaragdis:
Sparse Overcomplete Latent Variable Decomposition of Counts Data. NIPS 2007: 1313-1320 - [p2]Paris Smaragdis:
Probabilistic Decompositions of Spectra for Sound Separation. Blind Speech Separation 2007: 365-386 - 2006
- [c9]Bhiksha Raj, Madhusudana V. S. Shashanka, Paris Smaragdis:
Latent Dirichlet Decomposition for Single Channel Speaker Separation. ICASSP (5) 2006: 821-824 - [c8]Madhusudana V. S. Shashanka, Paris Smaragdis:
Secure Sound Classification: Gaussian Mixture Models. ICASSP (3) 2006: 1088-1091 - 2005
- [c7]Dhananjay Bansal, Bhiksha Raj, Paris Smaragdis:
Bandwidth expansion of narrowband speech using non-negative matrix factorization. INTERSPEECH 2005: 1505-1508 - [c6]Bhiksha Raj, Rita Singh, Paris Smaragdis:
Recognizing speech from simultaneous speakers. INTERSPEECH 2005: 3317-3320 - [p1]Paris Smaragdis:
Exploiting Redundancy to Construct Listening Systems. Speech Separation by Humans and Machines 2005: 83-95 - 2004
- [c5]Paris Smaragdis:
Non-negative Matrix Factor Deconvolution; Extraction of Multiple Sound Sources from Monophonic Inputs. ICA 2004: 494-499 - [c4]Paris Smaragdis:
Discovering auditory objects through non-negativity constraints. SAPA@INTERSPEECH 2004: 161 - 2002
- [c3]Brian Whitman, Paris Smaragdis:
Combining Musical and Cultural Features for Intelligent Style Detection. ISMIR 2002 - 2000
- [c2]Richard Boulanger, Paris Smaragdis, John ffitch:
Scanned Synthesis: An Introduction and Demonstration of a New Synthesis and Signal Processing Technique. ICMC 2000
1990 – 1999
- 1998
- [j1]Paris Smaragdis:
Blind separation of convolved mixtures in the frequency domain. Neurocomputing 22(1-3): 21-34 (1998) - 1996
- [c1]Michael A. Casey, Paris Smaragdis:
NetSound: Realtime Audio from Semantic Descriptions. ICMC 1996
Coauthor Index
manage site settings
To protect your privacy, all features that rely on external API calls from your browser are turned off by default. You need to opt-in for them to become active. All settings here will be stored as cookies with your web browser. For more information see our F.A.Q.
Unpaywalled article links
Add open access links from 
to the list of external document links (if available).
Privacy notice: By enabling the option above, your browser will contact the API of unpaywall.org to load hyperlinks to open access articles. Although we do not have any reason to believe that your call will be tracked, we do not have any control over how the remote server uses your data. So please proceed with care and consider checking the Unpaywall privacy policy.
Archived links via Wayback Machine
For web page which are no longer available, try to retrieve content from the 
of the Internet Archive (if available).
Privacy notice: By enabling the option above, your browser will contact the API of archive.org to check for archived content of web pages that are no longer available. Although we do not have any reason to believe that your call will be tracked, we do not have any control over how the remote server uses your data. So please proceed with care and consider checking the Internet Archive privacy policy.
Reference lists
Add a list of references from 
, 
, and 
to record detail pages.
load references from crossref.org and opencitations.net
Privacy notice: By enabling the option above, your browser will contact the APIs of crossref.org, opencitations.net, and semanticscholar.org to load article reference information. Although we do not have any reason to believe that your call will be tracked, we do not have any control over how the remote server uses your data. So please proceed with care and consider checking the Crossref privacy policy and the OpenCitations privacy policy, as well as the AI2 Privacy Policy covering Semantic Scholar.
Citation data
Add a list of citing articles from and to record detail pages.
load citations from opencitations.net
Privacy notice: By enabling the option above, your browser will contact the API of opencitations.net and semanticscholar.org to load citation information. Although we do not have any reason to believe that your call will be tracked, we do not have any control over how the remote server uses your data. So please proceed with care and consider checking the OpenCitations privacy policy as well as the AI2 Privacy Policy covering Semantic Scholar.
OpenAlex data
Load additional information about publications from 
.
Privacy notice: By enabling the option above, your browser will contact the API of openalex.org to load additional information. Although we do not have any reason to believe that your call will be tracked, we do not have any control over how the remote server uses your data. So please proceed with care and consider checking the information given by OpenAlex.
last updated on 2024-09-30 00:57 CEST by the dblp team
all metadata released as open data under CC0 1.0 license
see also: Terms of Use | Privacy Policy | Imprint
dblp was originally created in 1993 at:
since 2018, dblp has been operated and maintained by:
the dblp computer science bibliography is funded and supported by:
