Related papers: Sign Language Recognition using Parallel Bidirecti…
In modern society, people should not be identified based on their disability, rather, it is environments that can disable people with impairments. Improvements to automatic Sign Language Recognition (SLR) will lead to more enabling…
Independent Sign Language Recognition is a complex visual recognition problem that combines several challenging tasks of Computer Vision due to the necessity to exploit and fuse information from hand gestures, body features and facial…
We propose a novel approach to semi-supervised automatic speech recognition (ASR). We first exploit a large amount of unlabeled audio data via representation learning, where we reconstruct a temporal slice of filterbank features from past…
Natural Language Processing (NLP) and Voice Recognition agents are rapidly evolving healthcare by enabling efficient, accessible, and professional patient support while automating grunt work. This report serves as my self project wherein…
Embedding-based retrieval models have made significant strides in retrieval-augmented generation (RAG) techniques for text and multimodal large language models (LLMs) applications. However, when it comes to speech larage language models…
This paper explores speculative speech recognition (SSR), where we empower conventional automatic speech recognition (ASR) with speculation capabilities, allowing the recognizer to run ahead of audio. We introduce a metric for measuring SSR…
Sign language is the primary communication mode for 72 million hearing-impaired individuals worldwide, necessitating effective bidirectional Sign Language Production and Sign Language Translation systems. However, functional bidirectional…
Evaluating sign language generation is often done through back-translation, where generated signs are first recognized back to text and then compared to a reference using text-based metrics. However, this two-step evaluation pipeline…
. Continuous Sign Language Recognition (CSLR) is a long challenging task in Computer Vision due to the difficulties in detecting the explicit boundaries between the words in a sign sentence. To deal with this challenge, we propose a…
Sign Languages (SL) serve as the primary mode of communication for the Deaf and Hard of Hearing communities. Deep learning methods for SL recognition and translation have achieved promising results. However, Sign Language Production (SLP)…
The recent surge in large language models has automated translations of spoken and written languages. However, these advances remain largely inaccessible to American Sign Language (ASL) users, whose language relies on complex visual cues.…
Structured prediction tasks, like machine translation, involve learning functions that map structured inputs to structured outputs. Recurrent Neural Networks (RNNs) have historically been a popular choice for such tasks, including in…
Reservoir computing (RC), is a class of computational methods such as Echo State Networks (ESN) and Liquid State Machines (LSM) describe a generic method to perform pattern recognition and temporal analysis with any non-linear system. This…
Reservoir computing (RC) can efficiently process time-series data by transferring the input signal to randomly connected recurrent neural networks (RNNs), which are referred to as a reservoir. The high-dimensional representation of…
Bit-stream recognition (BSR) has many applications, such as forensic investigations, detection of copyright infringement, and malware analysis. We propose the first BSR that takes a bare input bit-stream and outputs a class label without…
Many technologies for human-computer interaction have been designed for hearing individuals and depend upon vocalized speech, precluding users of American Sign Language (ASL) in the Deaf community from benefiting from these advancements.…
Composed image retrieval (CIR) is the task of retrieving specific images by using a query that involves both a reference image and a relative caption. Most existing CIR models adopt the late-fusion strategy to combine visual and language…
Multilingual end-to-end(E2E) models have shown a great potential in the expansion of the language coverage in the realm of automatic speech recognition(ASR). In this paper, we aim to enhance the multilingual ASR performance in two ways,…
Optical packet header recognition is an important signal processing task of optical communication networks. In this work, we propose an all-optical reservoir, consisting of integrated double-ring resonators (DRRs) as nodes, for fast and…
Self-supervised learning (SSL) models have achieved considerable improvements in automatic speech recognition (ASR). In addition, ASR performance could be further improved if the model is dedicated to audio content information learning…