research
∙
07/12/2023
Sumformer: A Linear-Complexity Alternative to Self-Attention for Speech Recognition
Modern speech recognition systems rely on self-attention. Unfortunately,...
share
research
∙
11/08/2022
Cross-Attention is all you need: Real-Time Streaming Transformers for Personalised Speech Enhancement
Personalised speech enhancement (PSE), which extracts only the speech of...
research
∙
10/26/2021
Defensive Tensorization
We propose defensive tensorization, an adversarial defence technique tha...
research
∙
08/11/2020
Bunched LPCNet : Vocoder for Low-cost Neural Text-To-Speech Systems
LPCNet is an efficient vocoder that combines linear prediction and deep ...
research
∙
08/06/2020
Iterative Compression of End-to-End ASR Model using AutoML
Increasing demand for on-device Automatic Speech Recognition (ASR) syste...
research
∙
08/21/2019
MobiSR: Efficient On-Device Super-Resolution through Heterogeneous Mobile Processors
In recent years, convolutional networks have demonstrated unprecedented ...
research
∙
09/23/2017
Cross-modal Recurrent Models for Weight Objective Prediction from Multimodal Time-series Data
We analyse multimodal time-series data corresponding to weight, sleep an...
research
∙
12/25/2013