A5076299882- Speech Recognition and Synthesis
- Speech and Audio Processing
- Music and Audio Processing
- Additive Manufacturing and 3D Printing Technologies
- Brain Tumor Detection and Classification
- Advanced Adaptive Filtering Techniques
- Machine Learning in Healthcare
- AI in cancer detection
- Mitochondrial Function and Pathology
- Text and Document Classification Technologies
- Advanced Computing and Algorithms
- Domain Adaptation and Few-Shot Learning
- Head and Neck Anomalies
- Manufacturing Process and Optimization
- Advanced Neural Network Applications
- Dental Research and COVID-19
- COVID-19 epidemiological studies
- Digital Transformation in Industry
- COVID-19 diagnosis using AI
- Autism Spectrum Disorder Research
- Genetic Neurodegenerative Diseases
- COVID-19 Pandemic Impacts
- Voice and Speech Disorders
- Artificial Intelligence in Healthcare
- COVID-19 impact on air quality
Chitkara University
2020-2024
Lovely Professional University
2021
National University of Singapore
2021
Singapore University of Technology and Design
2021
Instituto Politécnico de Leiria
2021
Alzheimer’s disease (AD) is one of the most important causes mortality in elderly people, and it often challenging to use traditional manual procedures when diagnosing a early stages. The successful implementation machine learning (ML) techniques has also shown their effectiveness its reliability as better options for an diagnosis AD. But heterogeneous dimensions composition data have undoubtedly made diagnostics more difficult, needing sufficient model choice overcome difficulty. Therefore,...
Objective: To propose a theoretical formulation of engeletin-nanostructured lipid nanocarriers for improved delivery and increased bioavailability in treating Huntington's disease (HD). Methods: We conducted literature review the pathophysiology HD limitations currently available medications. also reviewed potential therapeutic benefits engeletin, flavanol glycoside, through Keap1/nrf2 pathway. then proposed across blood-brain barrier (BBB) bioavailability. Results: is an autosomal dominant...
The diagnosis and classification of autism spectrum disorder (ASD) presents anatomical difficulty owing to the existence a wide range symptoms that may be organized into many categories. present research investigates efficacy machine learning methods for facilitating recognition individuals who have been diagnosed with ASD. primary aim this study has assess effectiveness multiple algorithms based on in identifying intricate patterns seen datasets related ASD, which includes diagnostic...
The development of an Automatic Speech Recognition (ASR) system for children has been a significant difficulty because the substantial inherent heterogeneity in physical traits, articulation patterns, and mannerisms shown by each individual child. Moreover, limited availability quantities children's speech data may be linked to variances vocal-tract geometries resulting from anatomical physiological factors. present study aims address aforementioned issues conducting into advancement voice...
Processing of children's speech is always challenging due to data scarcity and inefficient modelling input feature vectors. Accuracy the phase dependent upon extracted features. In this paper, posterior probabilities are estimated over a phone set using first discriminatively trained model through neural-net pre-processor. This Neural Network (NN) classifier on original then context-independent Tandem-NN system. The output vectors employed as default features which processed Deep...
Alzheimer's disease (AD) is a long-term condition that causes brain areas such as memory, recognition, judgment, and speech to deteriorate. Classification of AD using neuroimaging data like MRI artificial intelligence has become focus current research. Likewise, deep learning recent breakthrough in computer vision accelerated similar However, fundamental shortcomings algorithms include their dependency on wide range training datasets the need for rigorous optimization neural network...
Development of a native language robust ASR framework is very challenging as well an active area research. Although urge for investigation effective front-end back-end approaches are required tackling environment differences, large training complexity and inter-speaker variability in achieving success recognition system. In this paper, four approaches: mel-frequency cepstral coefficients (MFCC), Gammatone frequency (GFCC), relative spectral-perceptual linear prediction (RASTA-PLP)...
Alzheimer's disease is a severe neurological disorder having major influence on substantial portion of the popu-lation. The prompt detection this condition crucial, and speech analysis may play crucial role in facilitating efficient treatment care. main aim research has been to investigate significance timely identification signal abnormalities associated with order provide effective therapy interventions improve man-agement. study used Mel Frequency Cepstral Coefficients (MFCC) framework,...
The development of optimal solutions in un-favourable acoustic conditions has become a crucial step guaranteeing the durability and dependability automated speech recognition (ASR) systems across many real-world applications. study aims to enhance efficiency low-resource ASR scenarios when conventional exhibit sub-optimal performance. proposed methodology performance Punjabi spoken digit noisy situations with limited resources. This is achieved via use multidimensional feature extraction...
The usage of Automatic Speaker Verification (ASV) in educational contexts has grown as a result measurements the speech signal claimed identity's native tongue. Even though resource-rich languages have received lot attention, low-resource languages, like Punjabi, still require work to be done on development ASV systems. In this study, an effort been put forth create system based i-vector for children while authenticating student's dialects Punjab region. Additionally, it determined how...
Abstract In real-life applications, noise originating from different sound sources modifies the characteristics of an input signal which affects development enhanced ASR system. This contamination degrades quality and comprehension speech variables while impacting performance human-machine communication systems. paper aims to minimise challenges by using a robust feature extraction methodology through introduction optimised filtering technique. Initially, evaluations for enhancing signals...
Within the field of speech recognition, a significant obstacle occurs when faced with low-resource situations charac-terized by scarcity accessible data, which is also het-erogeneous in nature. This becomes more challenging considering aspect clinical environments, where accurate transcription utmost significance identification and man-agement language disorders. The current manual methodologies used for development models (LMs) recognition often encounter difficulties scenarios, exhibiting...