Get our free extension to see links to code for papers anywhere online!

Chrome logo Add to Chrome

Firefox logo Add to Firefox

Picture for Paris Smaragdis

Sound Event Detection with Adaptive Frequency Selection


May 17, 2021
Zhepei Wang, Jonah Casebeer, Adam Clemmitt, Efthymios Tzinis, Paris Smaragdis

* Submitted to IEEE Workshop on Applications of Signal Processing to Audio and Acoustics 

  Access Paper or Ask Questions

Differentiable Signal Processing With Black-Box Audio Effects


May 11, 2021
Marco A. Martínez Ramírez, Oliver Wang, Paris Smaragdis, Nicholas J. Bryan

* Presented at the IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP), June 2021. Source code, demo and audio examples: https://mchijmma.github.io/DeepAFx/ 

  Access Paper or Ask Questions

Separate but Together: Unsupervised Federated Learning for Speech Enhancement from Non-IID Data


May 11, 2021
Efthymios Tzinis, Jonah Casebeer, Zhepei Wang, Paris Smaragdis

* Submitted to WASPAA 21 

  Access Paper or Ask Questions

Point Cloud Audio Processing


May 06, 2021
Krishna Subramani, Paris Smaragdis

* Submitted to WASPAA 2021, Code: https://github.com/SubramaniKrishna/point-cloud-audio 

  Access Paper or Ask Questions

Compute and memory efficient universal sound source separation


Mar 03, 2021
Efthymios Tzinis, Zhepei Wang, Xilin Jiang, Paris Smaragdis

* Journal submission. arXiv admin note: substantial text overlap with arXiv:2007.06833 

  Access Paper or Ask Questions

Optimizing Short-Time Fourier Transform Parameters via Gradient Descent


Oct 28, 2020
An Zhao, Krishna Subramani, Paris Smaragdis

* Submitted for ICASSP 2021 

  Access Paper or Ask Questions

Unified Gradient Reweighting for Model Biasing with Applications to Source Separation


Oct 25, 2020
Efthymios Tzinis, Dimitrios Bralios, Paris Smaragdis


  Access Paper or Ask Questions

Sudo rm -rf: Efficient Networks for Universal Audio Source Separation


Jul 14, 2020
Efthymios Tzinis, Zhepei Wang, Paris Smaragdis

* accepted to MLSP 2020 

  Access Paper or Ask Questions

Two-Step Sound Source Separation: Training on Learned Latent Targets


Oct 23, 2019
Efthymios Tzinis, Shrikant Venkataramani, Zhepei Wang, Cem Subakan, Paris Smaragdis

* Submitted to ICASSP 2020 

  Access Paper or Ask Questions

Continual Learning of New Sound Classes using Generative Replay


Jun 03, 2019
Zhepei Wang, Cem Subakan, Efthymios Tzinis, Paris Smaragdis, Laurent Charlin


  Access Paper or Ask Questions

Deep Tensor Factorization for Spatially-Aware Scene Decomposition


May 03, 2019
Jonah Casebeer*, Michael Colomb*, Paris Smaragdis

* 5 pages, 5 figures, submitted to WASPAA 2019 

  Access Paper or Ask Questions

Unsupervised Deep Clustering for Source Separation: Direct Learning from Mixtures using Spatial Information


Nov 05, 2018
Efthymios Tzinis, Shrikant Venkataramani, Paris Smaragdis

* Submitted to ICASSP 2019 

  Access Paper or Ask Questions

Learning the Base Distribution in Implicit Generative Models


Mar 13, 2018
Cem Subakan, Oluwasanmi Koyejo, Paris Smaragdis


  Access Paper or Ask Questions

Generative Adversarial Source Separation


Oct 30, 2017
Cem Subakan, Paris Smaragdis


  Access Paper or Ask Questions

Supervised and Unsupervised Speech Enhancement Using Nonnegative Matrix Factorization


Sep 15, 2017
Nasser Mohammadiha, Paris Smaragdis, Arne Leijon

* IEEE Trans. Audio, Speech and Language Process., vol. 21, no. 10, Oct. 2013 

  Access Paper or Ask Questions

Diagonal RNNs in Symbolic Music Modeling


Apr 19, 2017
Y. Cem Subakan, Paris Smaragdis

* Submitted to Waspaa 2017 

  Access Paper or Ask Questions

NoiseOut: A Simple Way to Prune Neural Networks


Nov 18, 2016
Mohammad Babaeizadeh, Paris Smaragdis, Roy H. Campbell


  Access Paper or Ask Questions

Bitwise Neural Networks


Jan 22, 2016
Minje Kim, Paris Smaragdis

* This paper was presented at the International Conference on Machine Learning (ICML) Workshop on Resource-Efficient Machine Learning, Lille, France, Jul. 6-11, 2015 

  Access Paper or Ask Questions

Joint Optimization of Masks and Deep Recurrent Neural Networks for Monaural Source Separation


Oct 01, 2015
Po-Sen Huang, Minje Kim, Mark Hasegawa-Johnson, Paris Smaragdis

* IEEE/ACM Transactions on Audio, Speech, and Language Processing, vol.23, no.12, pp.2136-2147, Dec. 2015 

  Access Paper or Ask Questions

A Dictionary Learning Approach for Factorial Gaussian Models


Aug 18, 2015
Y. Cem Subakan, Johannes Traa, Paris Smaragdis, Noah Stein


  Access Paper or Ask Questions