Silent voice: harnessing deep learning for lip-reading in Bangla

Silent voice: harnessing deep learning for lip-reading in Bangla

This thesis is submitted in partial fulfillment of the requirements for the degree of Bachelor of Science in Computer Science and Engineering, 2024.

Bibliografiska uppgifter
Huvudupphovsmän:	Shaheen, Munia, Ifti, Akib Zabed, Hassan, Ariful, Hossain, Junaed
Övriga upphovsmän:	Hossain, Muhammad Iqbal
Materialtyp:	Lärdomsprov
Språk:	English
Publicerad:	Brac University 2024
Ämnen:	Convolutional neural network (CNN) Recurrent neural network (RNN) Lip feature extraction Lip-reading Deep learning Machine learning Neural networks (Computer science)
Länkar:	http://hdl.handle.net/10361/22768

Liknande verk

A viseme recognition system using lip curvature and neural networks to detect Bangla vowels
av: Akhter, Nahid
Publicerad: (2017)

Sound classification using deep learning for hard of hearing and deaf people
av: Habib, Md.Adnan, et al.
Publicerad: (2022)

A conventional & deep learning strategy for analyzing & detecting Bengali fake news in online medium
av: Ahmed, Istiak, et al.
Publicerad: (2023)

Clustering and detection of good and bad rail line anchors from images
av: Islam, Samiul, et al.
Publicerad: (2017)

Semantic text extraction from CAPTCHA using Neural Networking
av: Chowdhury, Iftekhar Kabir, et al.
Publicerad: (2022)

Heartbeat sound feature extraction and classification
av: Bibrity, Fariha Chowdhury, et al.
Publicerad: (2020)

Deep learning based predictive analytics for decentralized content caching in hierarchical edge networks
av: Chakraborty, Dhruba, et al.
Publicerad: (2022)

Intracranial hemorrhage detection using CNN-LSTM fusion model
av: Ahmed, Kazi sabab, et al.
Publicerad: (2022)

Leveraging sequential deep learning models for detecting multitude of human action categories
av: Pranta, Kazi Al Refat, et al.
Publicerad: (2024)

Detection of handwritten text using convolutional neural network
av: Jasim, Rabib Bin, et al.
Publicerad: (2024)

ROBB: recurrent proximal policy optimization reinforcement learning for optimal block formation in bitcoin blockchain network
av: Dutta, Amit
Publicerad: (2024)

Visual object classification from fMRI data
av: Newaz, Syed Mishar, et al.
Publicerad: (2022)

Emotion recognition from facial expression of autism spectrum disordered children using image processing and machine learning algorithms
av: Tasnim, Nishat, et al.
Publicerad: (2019)

An android application to predict human activity using a deep learning LSTM model
av: Sikder, Debabrata
Publicerad: (2024)

Prediction of acute lymphoid leukemia using Privacy Preserving Neural Network
av: Khilji, Ishfaque Qamar, et al.
Publicerad: (2021)

Music genre classification with convolutional neural network
av: Chowdhury, Masud, et al.
Publicerad: (2022)

Automated fabric color prediction
av: Muhtashima, Fawzia, et al.
Publicerad: (2024)

Efficient image processing and machine learning approach for predicting retinal diseases
av: Hasib, Mehadi Hasan, et al.
Publicerad: (2021)

Analysis of uncertainty in different neural network structures using monte carlo dropout
av: Islam, Md. Farhadul, et al.
Publicerad: (2024)

Demand forecasting on supply chain using ML and NN
av: Hridi, Naoshin Anzum, et al.
Publicerad: (2023)

A machine learning approach to detect DeepFake videos
av: Hassan, Md. Mahedi, et al.
Publicerad: (2021)

An analysis of word sense disambiguation in Bangla and English using supervised learning and a deep neural network classifier
av: Pasha, Maroof Ur Rahman
Publicerad: (2016)

KDANet: optical recognition for Bangla language using deep neural networks
av: Rabbi, Kazi Kamruzzaman, et al.
Publicerad: (2023)

Pneumonia Disease detection using the convolutional neural network
av: Ashrafee, Md. Iftid, et al.
Publicerad: (2024)

Learning a deep neural network for predicting phishing website
av: Das, Robat, et al.
Publicerad: (2019)

Recurrent neural network classiﬁer for three layer conceptual network and performance evaluation
av: Md. Khalilur, Rhaman, et al.
Publicerad: (2016)

Predicting temperature of major cities using machine learning and deep learning
av: Jaharabi, Wasiou, et al.
Publicerad: (2024)

Traumatic meningeal enhancement detection by deep learning-based biomedical image analysis and handcrafted features extraction
av: Uddin, Mohammad Sakib, et al.
Publicerad: (2024)

Bang-lish sentiment classification using deep learning
av: Saleheen, Abrar, et al.
Publicerad: (2023)

Real-time fire detection based on feature analysis using enhanced color segmentation and novel foreground extraction
av: Khan, Rubayat Ahmed
Publicerad: (2022)

An efficient deep learning approach to classify white blood cells
av: Turja, Afif Ibna Kadir Khan, et al.
Publicerad: (2024)

One voice is all you need: a one-shot approach to recognize you
av: Dipto, Shahriar Rumi, et al.
Publicerad: (2022)

Automated image caption generator in Bangla using multimodal learning
av: Rodoshi, Mashiat Hasin, et al.
Publicerad: (2023)

Emotion detection from frontal facial image
av: Hussain, Sakib
Publicerad: (2014)

Malware Detection Using Neural Network
av: Kayum, Syed Irfan, et al.
Publicerad: (2021)

Crowd source based traffic analysis using machine learning algorithm
av: Orthy, Marzia Khan, et al.
Publicerad: (2018)

Analysis of malware prediction based on infection rate using machine learning techniques
av: Zawad, Safir, et al.
Publicerad: (2020)

Bangla license plate recognition using convolutional neural networks (CNN)
av: Rahman, M M Shaifur
Publicerad: (2018)

Deep Learning based Medicinal Plants Leaf Recognition
av: Mahalanabish, Tonusri
Publicerad: (2023)

Towards solving perception based autonomous driving assistant system
av: Hossain, Md. Arafat, et al.
Publicerad: (2022)