Search Results for author:
Found 6 papers, 4 papers with code
Challenges and Opportunities of Speech Recognition for Bengali Language
Speech recognition is a language-dependent system constructed directly based on the linguistic and textual properties of any language.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+1
End-to-End Optical Character Recognition for Bengali Handwritten Words
Further, we experiment with two different recurrent neural networks (RNN) methods, LSTM and GRU.
Optical Character Recognition
Optical Character Recognition (OCR)
U-vectors: Generating clusterable speaker embedding from unlabeled data
The robustness of a speaker recognition system mainly depends on the extraction process of speech embeddings, which are primarily pre-trained on a large-scale dataset.
FabricNet: A Fiber Recognition Architecture Using Ensemble ConvNets
The FabricNet can recognize a large scale of fibers by only utilizing a surface image of fabric.
A Lightweight Speaker Recognition System Using Timbre Properties
It also introduces new features that are used for both speaker verification and identification tasks.
AutoEmbedder: A semi-supervised DNN embedding system for clustering
Deep clustering method downsamples high dimensional data, which may also relate clustering loss.
