This book constitutes the revised selected papers of the Third International Conference on Speech and Language Technologies for Low-Resource Languages, SPELLL 2024, held in Chennai, India, during December 4–6, 2024. The 44 full papers and 11 short papers  included in these conference proceedings were carefully reviewed and selected from 120 submissions.They are divided into the following topical sections : Speech Processing and Spoken Language Understanding; Syntax, Semantics and Pragmatics; Advancements in Multilingual NLP: Resources,Processing, and Generation; Multimodality and Language Grounding to Vision and Robotics; Sentiment Analysis and Language-Specific Applications; Misinformation, Bias, and Mental Health Detection; Workshop 1: Workshop on Multimodal Machine Learning in Low-Resource Languages (MMLow 2024);Workshop 2: Workshop on Low Resource Cross Domain, Cross Lingual, Cross Modal Content Analysis –Multimedia and Generative AI; Workshop 3: Workshop on Fake News Detection in Low-Resource Languages.

Table of Contents:
.- Speech Processing and Spoken Language Understanding. .- A Comprehensive Malayalam Speech Database for Forensic Speaker Profiling and Authentication in Varied Acoustic Environments. .- Towards End-To-End Speech Synthesis for Tigrinya Language. .- An Effective LSTM – Autoencoder approach with Acoustic Features in Indian Classical Music Raga Recognition. .- Automatic Assessment of Pathological Voice Quality using Machine Learning Approaches. .- Audio to Text Conversion using Deep Learning. .- Comparative Analysis of Speaker Diarization Results on Multi-LingualMulti Speaker Data and Single Speaker Data. .- Enhancing End-to-End Malayalam Automatic Speech Recognition with Language Model Augmentation. .- Developing Bodo Speech Recognition with Kaldi. .- Syntax, Semantics and Pragmatics. .- A Deep Learning Based Approach to Detect Paraphrase in Healthcare. .- Enhancing Machine Translation Performance: A Comparative Study of Fine Tuning the MBart-mmt Model. .- Translation of Sanskrit (shlokas) -Malayalam Using Deep Learning Techniques. .- A Novel Multilingual Human-AI Collaborative Writing Tool for Indian Languages. .- Advancements in Multilingual NLP: Resources, Processing, and Generation. .- TamilFacts: A Comprehensive Multimodal Dataset of Fact-Checked Social Media Content in Tamil Language. .- A Comparative Study of Sentiment Analysis using Transformer Models and Text Augmentation Techniques for Bangla Text. .- Towards Automated Sanskrit Writing Correction: Evaluation on Large Language Models. .- Optimizing Tamil News Headline Generation with LoRA Techniques: Insights and Challenges. .- Corpus Creation for Racial Hoax in Code-Mixed Hindi-English Low Resource Text. .- Machine Learning Approaches for Tamil POS Tagging and Dependency Parsing. .- Multimodality and Language Grounding to Vision and Robotics. .- Empowering Consumers Through Advanced Technology:A Streamlit Web App Enabled Solution Leveraging OCR and BERT for Understanding Packaged Food Ingredients. .- Captioning-based Zero-Shot Visual Question Answering System. .- Enhancing Facial Emotion Recognition through Fine-tuning Vision Transformer Models. .- Optimizing OCR Model Performance : A Comparative Study ofBackbone Architectures and Hyperparameter Tuning. .- DravLangGuard: A Multimodal Approach for Hate Speech Detection in Dravidian Social Media. .- Multimodal Approaches to Speech Emotion Recognition. .- Sentiment Analysis and Language-Specific Applications. .- Sentiment Analysis on E-Commerce Based Product Reviews using Machine Learning Algorithms. .- Aspect-Based Sentiment Analysis. .- Detecting Hate Speech Towards the LGBT+ Population in Mexican Spanish Using Transformer Architectures. .- Kannada Stance Detection: Comparative Analysis of TF-IDF and BERT Embeddings with Traditional Classifiers. .- Enhancing COVID-19 Tweet Analysis with Transformer Hybrid Models. .- Misinformation, Bias, and Mental Health Detection. .- Explainable Approach Towards Fake News Detection in Malayalam using Hybrid Deep Learning Model. .- Fake News Detection in Hindi using Feature Fusion. .- Stress Identification in Telugu Using Large Language Models. .- AI Techniques for Detecting Depression in Social Media A Deep Learning and Transformer Approach. .- Multilingual Claim Span Identification using DaBERTa. .- Workshop 1: Workshop on Multimodal Machine Learning in Low-Resource Languages (MMLow 2024). .- Medical Image Captioning in Tamil using BLIP Model. .- Improving Malayalam Word Sense Disambiguation by exploiting various semantic features and vectorization method. .- Overruling Legal Sentence in Law using Domain Pre-trained BERT Variants. .- Textual Sarcasm Detection from Low-Resource Dravidian Languages using Deep Learning Techniques. .- Workshop 2: Workshop on Low Resource Cross Domain, Cross Lingual, Cross Modal Content Analysis –Multimedia and Generative AI. .- Automatic Correction of Disfluencies in Tamil Disfluent Text: A Rule-based Approach. .- Isolated Word Recognition in Malayalam using the Wavelet Scattering Transform and CNN. .- Workshop 3: Workshop on Fake News Detection in Low-Resource Languages. .- Fake News Detection in Dravidian Languages Using Transformers and Ensembles. .- Fake News Detection in Dravidian Languages: Comparative Analysis of Transformer Models, Ensemble Techniques, Traditional Classifiers, and Sentiment Influence on Prediction Performance. .- Fake News Detection using Multilingual BERT for English and Tamil Language. .- A Comparative Study of LLM-Based Techniques for Fake News Classification in Tamil.