In this version of the challenge organized at INTERSPEECH 2021, we are expanding both our training and test datasets to accommodate full band scenarios.
In this paper, we propose a novel idea to model speech and noise simultaneously in a two-branch convolutional neural network, namely SN-Net.
no code implementations • 23 Nov 2020 • Jayant Gupchup, Ashkan Aazami, Yaran Fan, Senja Filipi, Tom Finley, Scott Inglis, Marcus Asteborg, Luke Caroll, Rajan Chari, Markus Cozowicz, Vishak Gopal, Vinod Prakash, Sasikanth Bendapudi, Jack Gerrits, Eric Lau, Huazhou Liu, Marco Rossi, Dima Slobodianyk, Dmitri Birjukov, Matty Cooper, Nilesh Javar, Dmitriy Perednya, Sriram Srinivasan, John Langford, Ross Cutler, Johannes Gehrke
Large software systems tune hundreds of 'constants' to optimize their runtime performance.
In this challenge, we open source two large datasets to train AEC models under both single talk and double talk scenarios.
Acoustic echo cancellation Audio and Speech Processing Sound
no code implementations • 16 May 2020 • Chandan K. A. Reddy, Vishak Gopal, Ross Cutler, Ebrahim Beyrami, Roger Cheng, Harishchandra Dubey, Sergiy Matusevych, Robert Aichner, Ashkan Aazami, Sebastian Braun, Puneet Rana, Sriram Srinivasan, Johannes Gehrke
In this challenge, we open-sourced a large clean speech and noise corpus for training the noise suppression models and a representative test set to real-world scenarios consisting of both synthetic and real recordings.
no code implementations • 23 Jan 2020 • Chandan K. A. Reddy, Ebrahim Beyrami, Harishchandra Dubey, Vishak Gopal, Roger Cheng, Ross Cutler, Sergiy Matusevych, Robert Aichner, Ashkan Aazami, Sebastian Braun, Puneet Rana, Sriram Srinivasan, Johannes Gehrke
In this challenge, we open-source a large clean speech and noise corpus for training the noise suppression models and a representative test set to real-world scenarios consisting of both synthetic and real recordings.
In this paper, we study the effectiveness of these approaches in estimating aggregate properties on networks with missing attributes.
Our subjective MOS evaluation is the first large scale evaluation of Speech Enhancement algorithms that we are aware of.
13 code implementations • 26 Aug 2019 • Marc Lanctot, Edward Lockhart, Jean-Baptiste Lespiau, Vinicius Zambaldi, Satyaki Upadhyay, Julien Pérolat, Sriram Srinivasan, Finbarr Timbers, Karl Tuyls, Shayegan Omidshafiei, Daniel Hennes, Dustin Morrill, Paul Muller, Timo Ewalds, Ryan Faulkner, János Kramár, Bart De Vylder, Brennan Saeta, James Bradbury, David Ding, Sebastian Borgeaud, Matthew Lai, Julian Schrittwieser, Thomas Anthony, Edward Hughes, Ivo Danihelka, Jonah Ryan-Davis
OpenSpiel is a collection of environments and algorithms for research in general reinforcement learning and search/planning in games.
Optimization of parameterized policies for reinforcement learning (RL) is an important and challenging problem in artificial intelligence.
Rapid progress in deep reinforcement learning has made it increasingly feasible to train controllers for high-dimensional humanoid bodies.
We explain this by showing that $t_1 < 1$ caps the surrogate loss and $t_2 >1$ makes the predictive distribution have a heavy tail.
We consider an agent's uncertainty about its environment and the problem of generalizing this uncertainty across observations.
Ranked #7 on Atari Games on Atari 2600 Montezuma's Revenge
Scaling multinomial logistic regression to datasets with very large number of data points and classes is challenging.
In Reinforcement Learning (RL), it is common to use optimistic initialization of value functions to encourage exploration.