Robust speech parameters extraction for word recognition in noise using neural networks

1991 ◽  
Author(s):  
L. Barbier ◽  
G. Chollet
Keyword(s):  
Neural Networks ◽  
Word Recognition ◽  
Parameters Extraction

scholarly journals Handwritten Character and Digit Recognition Using Convolutional Neural Network

2021 ◽  
pp. 147-155
Author(s):  
Priyank Patel ◽  
Roshan Shinde ◽  
Siddhesh Raut ◽  
Sheetal Mahadik
Keyword(s):  
Neural Network ◽  
Neural Networks ◽  
Word Recognition ◽  
Convolutional Neural Network ◽  
Neural Net ◽  
Digit Recognition ◽  
Handwritten Character ◽  
On Line ◽  
Word Division ◽  
Precise Content

The necessity for quick and precise content section on little handheld PCs has prompted a resurgence of interest in on-line word recognition utilizing counterfeit neural Networks. Old style strategies are consolidated and improved to give strong recognition of hand-printed English content. The focal idea of a neural net as a character classifier gives a legitimate base to are cognition framework; long-standing issues comparative with preparing, speculation, division, probabilistic formalisms, and so forth, need to settled, notwithstanding, to instigate astounding execution. assortment of developments in a manner to utilize a neural net as a classifier in a very word recognizer are introduced: negative preparing, stroke twisting, adjusting, standardized yield blunder, mistake accentuation, numerous portrayals, quantized loads, and incorporated word division all add to effective and hearty execution.

scholarly journals AHWR-Net: offline handwritten amharic word recognition using convolutional recurrent neural network

2021 ◽  
Vol 3 (8) ◽  
Author(s):  
Fetulhak Abdurahman ◽  
Eyob Sisay ◽  
Kinde Anlay Fante
Keyword(s):  
Neural Network ◽  
Neural Networks ◽  
Feature Extraction ◽  
Word Recognition ◽  
Recurrent Neural Network ◽  
Text Recognition ◽  
Input Word ◽  
Handwritten Text ◽  
Handwritten Text Recognition ◽  
Word Images

AbstractAmharic ("Image missing") is the official language of the Federal Government of Ethiopia, with more than 27 million speakers. It uses an Ethiopic script, which has 238 core and 27 labialized characters. It is a low-resourced language, and a few attempts have been made so far for its handwritten text recognition. However, Amharic handwritten text recognition is challenging due to the very high similarity between characters. This paper presents a convolutional recurrent neural networks based offline handwritten Amharic word recognition system. The proposed framework comprises convolutional neural networks (CNNs) for feature extraction from input word images, recurrent neural network (RNNs) for sequence encoding, and connectionist temporal classification as a loss function. We designed a custom CNN model and compared its performance with three different state-of-the-art CNN models, including DenseNet-121, ResNet-50 and VGG-19 after modifying their architectures to fit our problem domain, for robust feature extraction from handwritten Amharic word images. We have conducted detailed experiments with different CNN and RNN architectures, input word image sizes, and applied data augmentation techniques to enhance performance of the proposed models. We have prepared a handwritten Amharic word dataset, HARD-I, which is available publicly for researchers. From the experiments on various recognition models using our dataset, a WER of 5.24 % and CER of 1.15 % were achieved using our best-performing recognition model. The proposed models achieve a competitive performance compared to existing models for offline handwritten Amharic word recognition.

scholarly journals A separable neural code in monkey IT enables perfect CAPTCHA decoding

2020 ◽  
Author(s):  
Harish Katti ◽  
S. P. Arun
Keyword(s):  
Neural Networks ◽  
Word Recognition ◽  
Machine Vision ◽  
Turing Test ◽  
Neural Code ◽  
Letter Recognition ◽  
Neural Recordings

ABSTRACTReading distorted letters is easy for us but so challenging for machine vision that it is used on websites as CAPTCHAs (Completely Automated Public Turing test to tell Computers and Humans Apart). How does our brain solve this problem? One solution is to have neurons invariant to letter distortions but selective for letter combinations. Another is for neurons to separately encode letter distortions and combinations. Here, we provide evidence for the latter using neural recordings in the monkey inferior temporal (IT) cortex. Neurons encoded letter distortions as a product of letter and distortion tuning, and letter combinations as a sum of letters. These rules were sufficient for perfect CAPTCHA decoding and were also present in neural networks trained for word recognition. Taken together, our findings suggest that a separable neural code enables efficient letter recognition.

Sign in / Sign up

Export Citation Format

Share Document