Picture for Tanay Sharma

Tanay Sharma

Audio-Visual Decision Fusion for WFST-based and seq2seq Models

Add code
Jan 29, 2020
Figure 1 for Audio-Visual Decision Fusion for WFST-based and seq2seq Models
Figure 2 for Audio-Visual Decision Fusion for WFST-based and seq2seq Models
Figure 3 for Audio-Visual Decision Fusion for WFST-based and seq2seq Models
Figure 4 for Audio-Visual Decision Fusion for WFST-based and seq2seq Models
Viaarxiv icon

LipReading with 3D-2D-CNN BLSTM-HMM and word-CTC models

Add code
Jun 25, 2019
Figure 1 for LipReading with 3D-2D-CNN BLSTM-HMM and word-CTC models
Figure 2 for LipReading with 3D-2D-CNN BLSTM-HMM and word-CTC models
Figure 3 for LipReading with 3D-2D-CNN BLSTM-HMM and word-CTC models
Figure 4 for LipReading with 3D-2D-CNN BLSTM-HMM and word-CTC models
Viaarxiv icon

Global SNR Estimation of Speech Signals using Entropy and Uncertainty Estimates from Dropout Networks

Add code
Apr 12, 2018
Figure 1 for Global SNR Estimation of Speech Signals using Entropy and Uncertainty Estimates from Dropout Networks
Figure 2 for Global SNR Estimation of Speech Signals using Entropy and Uncertainty Estimates from Dropout Networks
Figure 3 for Global SNR Estimation of Speech Signals using Entropy and Uncertainty Estimates from Dropout Networks
Figure 4 for Global SNR Estimation of Speech Signals using Entropy and Uncertainty Estimates from Dropout Networks
Viaarxiv icon