research
∙
07/06/2023
On-Device Constrained Self-Supervised Speech Representation Learning for Keyword Spotting via Knowledge Distillation
Large self-supervised models are effective feature extractors, but their...
share
research
∙
03/07/2023
Self-supervised speech representation learning for keyword-spotting with light-weight transformers
Self-supervised speech representation learning (S3RL) is revolutionizing...
research
∙
10/20/2021
Time-Domain Mapping Based Single-Channel Speech Separation With Hierarchical Constraint Training
Single-channel speech separation is required for multi-speaker speech re...
research
∙
06/14/2020
Recurrent Distillation based Crowd Counting
In recent years, with the progress of deep learning technologies, crowd ...
research
∙
06/20/2019
A Monaural Speech Enhancement Method for Robust Small-Footprint Keyword Spotting
Robustness against noise is critical for keyword spotting (KWS) in real-...
research
∙
04/15/2019
RHR-Net: A Residual Hourglass Recurrent Neural Network for Speech Enhancement
Most current speech enhancement models use spectrogram features that req...
research
∙
05/22/2018
Multimodal Affective Analysis Using Hierarchical Attention Strategy with Word-Level Alignment
Multimodal affective computing, learning to recognize and interpret huma...
research
∙
02/22/2018