Picture for Muhammad Mostafa Monowar

Muhammad Mostafa Monowar

Challenges and Opportunities of Speech Recognition for Bengali Language

Add code
Sep 27, 2021
Figure 1 for Challenges and Opportunities of Speech Recognition for Bengali Language
Figure 2 for Challenges and Opportunities of Speech Recognition for Bengali Language
Figure 3 for Challenges and Opportunities of Speech Recognition for Bengali Language
Figure 4 for Challenges and Opportunities of Speech Recognition for Bengali Language
Viaarxiv icon

End-to-End Optical Character Recognition for Bengali Handwritten Words

Add code
May 09, 2021
Figure 1 for End-to-End Optical Character Recognition for Bengali Handwritten Words
Figure 2 for End-to-End Optical Character Recognition for Bengali Handwritten Words
Figure 3 for End-to-End Optical Character Recognition for Bengali Handwritten Words
Figure 4 for End-to-End Optical Character Recognition for Bengali Handwritten Words
Viaarxiv icon

U-vectors: Generating clusterable speaker embedding from unlabeled data

Add code
Feb 07, 2021
Figure 1 for U-vectors: Generating clusterable speaker embedding from unlabeled data
Figure 2 for U-vectors: Generating clusterable speaker embedding from unlabeled data
Figure 3 for U-vectors: Generating clusterable speaker embedding from unlabeled data
Figure 4 for U-vectors: Generating clusterable speaker embedding from unlabeled data
Viaarxiv icon

FabricNet: A Fiber Recognition Architecture Using Ensemble ConvNets

Add code
Jan 14, 2021
Figure 1 for FabricNet: A Fiber Recognition Architecture Using Ensemble ConvNets
Figure 2 for FabricNet: A Fiber Recognition Architecture Using Ensemble ConvNets
Figure 3 for FabricNet: A Fiber Recognition Architecture Using Ensemble ConvNets
Figure 4 for FabricNet: A Fiber Recognition Architecture Using Ensemble ConvNets
Viaarxiv icon

A Lightweight Speaker Recognition System Using Timbre Properties

Add code
Oct 13, 2020
Figure 1 for A Lightweight Speaker Recognition System Using Timbre Properties
Figure 2 for A Lightweight Speaker Recognition System Using Timbre Properties
Figure 3 for A Lightweight Speaker Recognition System Using Timbre Properties
Figure 4 for A Lightweight Speaker Recognition System Using Timbre Properties
Viaarxiv icon

AutoEmbedder: A semi-supervised DNN embedding system for clustering

Add code
Jul 11, 2020
Figure 1 for AutoEmbedder: A semi-supervised DNN embedding system for clustering
Figure 2 for AutoEmbedder: A semi-supervised DNN embedding system for clustering
Figure 3 for AutoEmbedder: A semi-supervised DNN embedding system for clustering
Figure 4 for AutoEmbedder: A semi-supervised DNN embedding system for clustering
Viaarxiv icon