Code implementation for our ICPR, 2020 paper titled "Improving Word Recognition using Multiple Hypotheses and Deep Embeddings"

a simple word guessing game 🕹. Leave a star before you leave ⭐

Code implementation for our DAS, 2020 paper titled "Fused Text Recogniser and Deep Embeddings Improve Word Recognition and Retrieval"

Zilla-64: A Bangla Handwritten Word Dataset Of 64 Districts Name of Bangladesh and Recognition Using Holistic Approach

Implementation of PHOSNet and Pho(SC)Net for Word Recognition in Historical Documents. Implemented using Tensorflow 2.x

A graphical automata builder

A lightweight Python GUI application for handwriting recognition using TensorFlow and EMNIST dataset. Draw characters or load images to recognize handwritten text with real-time confidence scoring and character-by-character analysis.

The masked priming response to affix and stem priming: a large-scale online study

Project on Optical Character Recognition with the help of Tesseract-ocr.

This is a minimal code part of my assignment for the graduate course Speech Recognition

Flask web application recognizes a single word or number from an image based on deep learning word and digit recognition that combines a hybrid inference pipeline with the use of TensorFlow, a CNN + BiLSTM (CRNN) architecture, and CTC decoding.

A game where you have to find words that can be spelled with a root word

Analysing voice onset time (VOT) data using binary search and word similarity

Visualization of Interactive Activation (IA) model(1981) regarding letter perception in Simbrain (WORK example, demonstrating word superiority effect)

Simple audio recognition using multiple machine learning models

This system is a deep learning–based word recognition (OCR) web application built using TensorFlow, CNN + BiLSTM (CRNN) architecture, and CTC decoding, deployed with a Flask web interface.

My thesis dissertation at Universtat Pompeu Fabra (2024).

A desktop application for scoring word lists using whole word and phonemic scoring. Features 80% and 95% critical difference tables for validating hearing aid fittings and word recognition performance. Tables generated by Pairwise Monte Carlo simulation using methodology modified from Carney & Schlauch (2007).