Search Results for author:
Found 7 papers, 0 papers with code
Robustness to Multi-Modal Environment Uncertainty in MARL using Curriculum Learning
This work is the first to formulate the generalised problem of robustness to multi-modal environment uncertainty in MARL.
Synthetic Wave-Geometric Impulse Responses for Improved Speech Dereverberation
We present a novel approach to improve the performance of learning-based speech dereverberation using accurate synthetic datasets.
Reverberation as Supervision for Speech Separation
This paper proposes reverberation as supervision (RAS), a novel unsupervised loss function for single-channel reverberant speech separation.
Improving Reverberant Speech Separation with Multi-stage Training and Curriculum Learning
We present a novel approach that improves the performance of reverberant speech separation.
Audio-Visual Decision Fusion for WFST-based and seq2seq Models
In this work, we propose novel methods to fuse information from audio and visual modalities at inference time.
LipReading with 3D-2D-CNN BLSTM-HMM and word-CTC models
We also verify the method on a second dataset of $81$ speakers which we collected.
Global SNR Estimation of Speech Signals using Entropy and Uncertainty Estimates from Dropout Networks
This paper demonstrates two novel methods to estimate the global SNR of speech signals.
