31 citations · 122 across the 37 of their papers we have counts for
5 papers · 2 filters
Dynamic Kernels and Channel Attention for Low Resource Speaker Verification
Anna Ollerenshaw, Md Asif Jalal, Thomas Hain
State-of-the-art speaker verification frameworks have typically focused on developing models with increasingly deeper (more layers) and wider (number of channels) models to improve…
Deformable Temporal Convolutional Networks for Monaural Noisy Reverberant Speech Separation
William Ravenscroft, Stefan Goetze, Thomas Hain
Speech separation models are used for isolating individual speakers in many speech processing applications. Deep learning models have been shown to lead to state-of-the-art (SOTA)…
Utterance Weighted Multi-Dilation Temporal Convolutional Networks for Monaural Speech Dereverberation
William Ravenscroft, Stefan Goetze, Thomas Hain
Speech dereverberation is an important stage in many speech technology applications. Recent work in this area has been dominated by deep neural network models. Temporal convolution…
Receptive Field Analysis of Temporal Convolutional Networks for Monaural Speech Dereverberation
William Ravenscroft, Stefan Goetze, Thomas Hain
Speech dereverberation is often an important requirement in robust speech processing tasks. Supervised deep learning (DL) models give state-of-the-art performance for single-channe…
MetricGAN+/-: Increasing Robustness of Noise Reduction on Unseen Data
George Close, Thomas Hain, Stefan Goetze
Training of speech enhancement systems often does not incorporate knowledge of human perception and thus can lead to unnatural sounding results. Incorporating psychoacoustically mo…