Search Results for author: Sriram Srinivasan

Found 16 papers, 6 papers with code

Interspeech 2021 Deep Noise Suppression Challenge

1 code implementation6 Jan 2021 Chandan K A Reddy, Harishchandra Dubey, Kazuhito Koishida, Arun Nair, Vishak Gopal, Ross Cutler, Sebastian Braun, Hannes Gamper, Robert Aichner, Sriram Srinivasan

In this version of the challenge organized at INTERSPEECH 2021, we are expanding both our training and test datasets to accommodate full band scenarios.

Denoising Speech Quality

Interactive Speech and Noise Modeling for Speech Enhancement

no code implementations17 Dec 2020 Chengyu Zheng, Xiulian Peng, Yuan Zhang, Sriram Srinivasan, Yan Lu

In this paper, we propose a novel idea to model speech and noise simultaneously in a two-branch convolutional neural network, namely SN-Net.

Speaker Separation Speech Enhancement

ICASSP 2021 Acoustic Echo Cancellation Challenge: Datasets and Testing Framework

no code implementations10 Sep 2020 Kusha Sridhar, Ross Cutler, Ando Saabas, Tanel Parnamaa, Hannes Gamper, Sebastian Braun, Robert Aichner, Sriram Srinivasan

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

The INTERSPEECH 2020 Deep Noise Suppression Challenge: Datasets, Subjective Testing Framework, and Challenge Results

no code implementations16 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.

Speech Enhancement

The INTERSPEECH 2020 Deep Noise Suppression Challenge: Datasets, Subjective Speech Quality and Testing Framework

no code implementations23 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.

Speech Enhancement Speech Quality

Estimating Aggregate Properties In Relational Networks With Unobserved Data

no code implementations16 Jan 2020 Varun Embar, Sriram Srinivasan, Lise Getoor

In this paper, we study the effectiveness of these approaches in estimating aggregate properties on networks with missing attributes.

Relational Reasoning

A scalable noisy speech dataset and online subjective test framework

no code implementations17 Sep 2019 Chandan K. A. Reddy, Ebrahim Beyrami, Jamie Pool, Ross Cutler, Sriram Srinivasan, Johannes Gehrke

Our subjective MOS evaluation is the first large scale evaluation of Speech Enhancement algorithms that we are aware of.

Speech Enhancement

Actor-Critic Policy Optimization in Partially Observable Multiagent Environments

no code implementations NeurIPS 2018 Sriram Srinivasan, Marc Lanctot, Vinicius Zambaldi, Julien Perolat, Karl Tuyls, Remi Munos, Michael Bowling

Optimization of parameterized policies for reinforcement learning (RL) is an important and challenging problem in artificial intelligence.

Learning human behaviors from motion capture by adversarial imitation

1 code implementation7 Jul 2017 Josh Merel, Yuval Tassa, Dhruva TB, Sriram Srinivasan, Jay Lemmon, Ziyu Wang, Greg Wayne, Nicolas Heess

Rapid progress in deep reinforcement learning has made it increasingly feasible to train controllers for high-dimensional humanoid bodies.

Imitation Learning Motion Capture

Two-temperature logistic regression based on the Tsallis divergence

no code implementations19 May 2017 Ehsan Amid, Manfred K. Warmuth, Sriram Srinivasan

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.

Domain-Independent Optimistic Initialization for Reinforcement Learning

no code implementations16 Oct 2014 Marlos C. Machado, Sriram Srinivasan, Michael Bowling

In Reinforcement Learning (RL), it is common to use optimistic initialization of value functions to encourage exploration.

Cannot find the paper you are looking for? You can Submit a new open access paper.