Modern speech recognition systems rely on self-attention. Unfortunately,...
Personalised speech enhancement (PSE), which extracts only the speech of...
We propose defensive tensorization, an adversarial defence technique tha...
LPCNet is an efficient vocoder that combines linear prediction and deep
...
Increasing demand for on-device Automatic Speech Recognition (ASR) syste...
In recent years, convolutional networks have demonstrated unprecedented
...
We analyse multimodal time-series data corresponding to weight, sleep an...
We propose a sparse-coding framework for activity recognition in ubiquit...