-
Recurrent Distillation based Crowd Counting
In recent years, with the progress of deep learning technologies, crowd ...
06/14/2020 ∙ by Yue Gu, et al. ∙
0
∙
share
read it
-
A Monaural Speech Enhancement Method for Robust Small-Footprint Keyword Spotting
Robustness against noise is critical for keyword spotting (KWS) in real-...
06/20/2019 ∙ by Yue Gu, et al. ∙
0
∙
share
read it
-
RHR-Net: A Residual Hourglass Recurrent Neural Network for Speech Enhancement
Most current speech enhancement models use spectrogram features that req...
04/15/2019 ∙ by Jalal Abdulbaqi, et al. ∙
0
∙
share
read it
-
Multimodal Affective Analysis Using Hierarchical Attention Strategy with Word-Level Alignment
Multimodal affective computing, learning to recognize and interpret huma...
05/22/2018 ∙ by Yue Gu, et al. ∙
0
∙
share
read it
-
Deep Multimodal Learning for Emotion Recognition in Spoken Language
In this paper, we present a novel deep multimodal framework to predict h...
02/22/2018 ∙ by Yue Gu, et al. ∙
0
∙
share
read it
