activity
20202023
most citedCombining Spatial Clustering with LSTM Speech Models for Multichannel Speech Enhancement

2 citations · 4 across the 5 of their papers we have counts for

collaborators

6 papers

cs.LG2023

Finite Gaussian Neurons: Defending against adversarial attacks by making neural networks say "I don't know"

Felix Grezes

Since 2014, artificial neural networks have been known to be vulnerable to adversarial attacks, which can fool the network into producing wrong or nonsensical outputs by making hum…

cs.CL2022

Improving astroBERT using Semantic Textual Similarity

Felix Grezes, Thomas Allen, Sergi Blanco-Cuaresma +13

The NASA Astrophysics Data System (ADS) is an essential tool for researchers that allows them to explore the astronomy and astrophysics scientific literature, but it has yet to exp…

cs.HC20221 cited

Web accessibility trends and implementation in dynamic web applications

Timothy W. Hostetler, Shinyi Chen, Sergi Blanco-Cuaresma +12

The NASA Astrophysics Data System (ADS), a critical research service for the astrophysics community, strives to provide the most accessible and inclusive environment for the discov…

cs.SD20202 cited

Combining Spatial Clustering with LSTM Speech Models for Multichannel Speech Enhancement

Felix Grezes, Zhaoheng Ni, Viet Anh Trinh +1

Recurrent neural networks using the LSTM architecture can achieve significant single-channel noise reduction. It is not obvious, however, how to apply them to multi-channel inputs…

cs.SD20201 cited

Improved MVDR Beamforming Using LSTM Speech Models to Clean Spatial Clustering Masks

Zhaoheng Ni, Felix Grezes, Viet Anh Trinh +1

Spatial clustering techniques can achieve significant multi-channel noise reduction across relatively arbitrary microphone configurations, but have difficulty incorporating a detai…

cs.SD2020

Enhancement of Spatial Clustering-Based Time-Frequency Masks using LSTM Neural Networks

Felix Grezes, Zhaoheng Ni, Viet Anh Trinh +1

Recent works have shown that Deep Recurrent Neural Networks using the LSTM architecture can achieve strong single-channel speech enhancement by estimating time-frequency masks. How…