Neural Networks-based Speech Enhancement
Established: January 8, 2017
People
Contributing researchers
Sebastian Braun
Principal Researcher
Hannes Gamper
Principal Researcher
Matthai Philipose
Senior Principal Researcher
Ivan Tashev
Partner Software Architect
Past interns
Viet Anh Trinh
Unsupervised Speech Enhancement, 2021
City University of New York (CUNY), USA
Abu-Zaher Faridee
Non-Intrusive Multi-Task Speech Quality Assessment, 2021
University of Maryland, USA
Ali Aroudi
Geometry-constrained Beamforming Network for end-to-end Farfield Sound Source Separation, 2020
University of Oldenburg, Germany
Yangyang (Raymond) Xia
Real-time Single-channel Speech Enhancement with Recurrent Neural Networks, 2019
Carnegie Mellon University
Anderson Avila
Deep Neural Network Models for Audio Quality Assessment, 2018
Institut National de la Recherche Scientifique (INRS-EMT), Canada
Han Zao
High-Accuracy Neural-Network Models for Speech Enhancement, 2017
Carnegie Mellon University
Jong Hwan Ko
Efficient Neural-Network Design for Real-Time Speech Enhancement, 2017
Georgia Institute of Technology
Rasool Fakoor
Speech Enhancement With and Without Gradient Descent, 2017
University of Texas at Arlington
Yan-hui Tu
Regression Based Speech Enhancement with Neural Networks, 2017
University of Science and Technology of China, P. R. China
Seyedmahdad Mirsamadi
DNN-based Online Speech Enhancement Using Multitask Learning and Suppression Rule Estimation, 2015
University of Texas at Dallas
Consulting researchers
Chin-Hui Lee
Professeur
Georgia Tech