Comprehensive analysis and development of deep learning models for Bengali character’s spectrogram image classification in child speech: introduction of spectro SETNet

Comprehensive analysis and development of deep learning models for Bengali character’s spectrogram image classification in child speech: introduction of spectro SETNet

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

書目詳細資料
Main Authors:	Ahmed, Syed Istiaque, Hossain, Md. Jubayer, Hoque, Kayes Mohammad Bin, Tusher, Mahmadur Rahman, Islam, Sajedur
其他作者:	Alam, Md. Golam Rabiul
格式:	Thesis
語言:	English
出版:	Brac University 2024
主題:	Automatic speech recognition Character’s recognition Deep learning Mel-frequency spectrogram Spectro-SETNet Automatic speech recognition > Data processing. Deep learning (Machine learning). Spectrometer > Data processing.
在線閱讀:	http://hdl.handle.net/10361/24029

相似書籍

Classification of Bangla regional languages and recognition of artificial Bangla speech using deep learning
由: Hossain, Prommy Sultana
出版: (2022)

Fundamentals of speech recognition /
由: Rabiner, Lawrence R., 1943-
出版: (2009)

Statistical methods for speech recognition /
由: Jelinek, Frederick, 1932-
出版: (1997)

Statistical methods for speech recognition /
由: Jelinek, Frederick, 1932-
出版: (1997)

Speech and language processing : an introduction to natural language processing, computational linguistics, and speech recognition /
由: Jurafsky, Dan, 1962-
出版: (2000)

Novel approach to detect hate speech and profanity on online platforms
由: Pritha, Barha Meherun, et al.
出版: (2022)

Identifying hate speech of Bangla language text using natural language processing
由: Rahman, Mushfiqur, et al.
出版: (2024)

Predicting regional accents of Bengali language using deep learning
由: Ibrahim, Md. Abu, et al.
出版: (2022)

Identifying code-mixed and code-switched hateful remarks on social media using NLP
由: Sinha, Sumaiya, et al.
出版: (2024)

Bengali isolated speech recognition : a comparative analysis of the effects of data augmentation on HMM and DNN based acoustic models
由: Rashid, Warida, et al.
出版: (2018)

Voice recognition using machine learning and central database to enhance security system
由: Nur, Mir Md. Taosif, et al.
出版: (2022)

Behavior change analysis due to violent video gaming using deep learning models
由: Rahman, Akhlak Ur, et al.
出版: (2024)

Traffic sign recognition using deep learning
由: Amir, Afia Binte, et al.
出版: (2020)

Bangla speech recognition using 1D CNN and LSTM with different dimension reduction techniques
由: Nirjhor, S M Mahsanul Islam, et al.
出版: (2019)

Gender classification in Bangla language using deep learning-based voice analysis
由: Hakim, Talukder Juhaer, et al.
出版: (2024)

AVCL: Audio Video clustering for learning Conversation labeling using Neural Network and NLP
由: Chowdhury, Salman Mostafiz, et al.
出版: (2022)

Acoustic analysis of Bangla consonants
由: Alam, Firoj, et al.
出版: (2010)

Acoutstic analysis of Bangla consonants
由: Alam, Firoj, et al.
出版: (2010)

Image recognition by deep learning
由: Mohiuddin, Karishma, et al.
出版: (2018)

Audio recognition using feed forward neural network optimized by principle component analysis
由: Momo, Nusrat Suzana, et al.
出版: (2017)

Visual speech recognition using artificial neural networking
由: Sharmili, Nowshin, et al.
出版: (2018)

Computational analysis and detection of Bengali communal violent speech
由: Khondoker, Abdullah, et al.
出版: (2024)

Affordable voice assistive intelligent glass for visually impaired people in perspective of Bangladesh
由: Peyal, Md. Mahmudul Kabir, et al.
出版: (2021)

Shield key: a deep learning process for the generation of public & private keys using hybrid architecture in blockchain
由: Joy, Tanvir Ahmed, et al.
出版: (2021)

Shohojogi: an automated Bengali voice chat system for the banking customer services
由: Arnab, Kabir Abdur Rahman, et al.
出版: (2023)

Visual object recognition using deep convolutional neural network
由: Ahmed, Sabbir
出版: (2017)

Classification of respiratory diseases and COVID-19 from respiratory and cough sound using deep learning techniques
由: Ahasan, Md. Mubtasim, et al.
出版: (2022)

Voice impersonation detection using LSTM based RNN and explainable AI
由: Barua, Kawshik, et al.
出版: (2022)

Real time dynamic facial recognition of subject at motion using angular image
由: Tasneem, Sharah, et al.
出版: (2024)

Automatic attendance system using facial recognition
由: Sikdar, Tushar, et al.
出版: (2022)

Into the heart of Bangla speech: advancing speech sentiment recognition with semi-supervised multimodal machine learning model leveraging an iterative SHAP-based feature selection
由: Shruti, Abanti Chakraborty
出版: (2024)

A squeeze and excitation ResNeXt-based deep learning model for Bangla handwritten basic to compound character recognition
由: Khan, Mohammad Meraj
出版: (2022)

Isolated and continuous bangla speech recognition: implementation, performance and application perspective
由: Hasnat, Md. Abul, et al.
出版: (2010)

A deep learning approach to integrate human-level understanding in a Chatbot
由: Al Mamun, Amirul Islam, et al.
出版: (2021)

Damaged road detection using Image Processing and Deep Learning
由: Swadesh, Shimran Mahbub, et al.
出版: (2022)

Bangali Handwritten characters classification using Deep Convolutional Neural Network
由: Sikder, Shihab Uddin, et al.
出版: (2022)

Multiclass emotion classification by using Spectrogram image analysis: A CNN-XGBoost fusion approach
由: Esha, Ishraq Ahmed, et al.
出版: (2023)

Detection of violent activity in surveillance system using different deep learning techniques
由: Chakravorty, Tirthendu Prosad, et al.
出版: (2024)

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

Implementation of diffusion model in realistic face generation
由: Rahman, Abidur, et al.
出版: (2024)