Read more
This two-volume set, CCIS 2267 and 2268, constitutes the refereed proceedings of 5th International Conference on Artificial Intelligence and Speech Technology, AIST 2023, held in Delhi, India, during December 26-27, 2023.
The 71 papers presented in two volumes were carefully reviewed and selected from 235 submissions. Part I focuses on Speech Technology using AI and Part II focuses on AI innovations for CV and NLP. These volumes are organized in the following topical sections:
Part I: Trends and Applications in Speech Processing; Recent Trends in Speech and NLP; Emerging trends in Speech Processing; Advances in Computational Linguistics and NLP.
Part II: Recent Trends in Machine Learning and Deep Learning; Analysis using Hybrid technologies with Artificial Intelligence; Exploring New Horizons in Computer Vision Research; Applications of Machine Learning and Deep Learning.
List of contents
.- An Efficient Deep Learning based Seq2Seq Model for Abstractive Text summarization.
.- Text Scribe: Unveiling New Dimensions in Text Summarization.
.- GRUbBD-SM: Gated Recurrent Unit based Bot Detection on social media.
.- Scaling Language Boundaries: A Comparative Analysis of Multilingual Question-Answering Capabilities in Large Language Models.
.- Performing Text Segmentation to Improve OCR on Multi Scene Text.
.- Deep Learning Based Multilingual Voice Recognition System and Analytics for Organization Surveys.
.- Speech Emotion Recognition using Convolutional Neural Networks.
.- Hybrid Approach to The Personification of dialogue Agents.
.- MelSpectroNet: Enhancing Voice Authentication Security with AI-based Siamese Model and Noise Reduction for Seamless User Experience.
.- A framework for Information Retrieval using Domain Specific Dictionary: Illustration through enhancing the Intelligence Cycle.
.- Text-Independent Voiceprints Identification using Feed- Forward Back-propagation with layered strategies.
.- Email Bot- Voice Based Email System for Blind.
.- Empowering Hate Speech Detection: A Comparative Exploration of Deep Learning Models.
.- Hate Speech Detection Using Glove and BERT.
.- Santali Vowel Recognition: An Under-Resourced Tribal Language.
.- Revolutionizing Writing: Personalized Neural Classifier for Handwritten Text.
.- Hindi Speech Recognition using Deep Learning: A Review.
.- A Comprehensive Review of Instructional Tools and Applications for Dyslexic Learners.
.- Deep Learning-based Speech Recognition Models: Review.
.- Analysis of Acoustic Features for Gender Identification using Punjabi Speech Dataset.
.- Context Based Anaphora Resolution of English Discourses using Rule Based Approach.
.- Enhancing Named Entity Recognition with DistilBERT and Attention Ensemble Fusion.
.- Explaining Spectrograms in Machine Learning: A Study on Neural Networks for Speech Classification.
.- Speech Recognition using Adaptation of Whisper Models.
.- Voice Stress Analysis using Machine Learning.
.- Efficient Real-Time Indian Sign Language Fingerspelling Recognition in Natural Settings using Heuristics.
.- A Novel and Intelligent approach for Indian Locale Based Text-to-Speech Model by hybridizing Wave Net and Wave Glow with Mel-Spectrogram Analysis.
.- Optimization of Indian Sign Language Detection using Data Generators.
.- A Comparative Analysis of Deep Learning Architecture for Accurate Gender Classification using Vocal Data.
.- A Comprehensive Analysis on Kaldi-Based Speech Recognition for Low Resource Indian Languages.
.- Comparative Analysis of Deep Learning Models for Text Summarization on Hindi Corpus.
.- Tune into Your Feelings: NLP-Powered Emotion Driven Music Recommender System.
.- Recent Trends in text to Speech Synthesis in Context with Indian Languages.
.- Advanced Speech Emotion Recognition in Malayalam Accented Speech: Analyzing Unsupervised and Supervised Approaches.
Summary
This two-volume set, CCIS 2267 and 2268, constitutes the refereed proceedings of 5th International Conference on Artificial Intelligence and Speech Technology, AIST 2023, held in Delhi, India, during December 26–27, 2023.
The 71 papers presented in two volumes were carefully reviewed and selected from 235 submissions. Part I focuses on Speech Technology using AI and Part II focuses on AI innovations for CV and NLP. These volumes are organized in the following topical sections:
Part I: Trends and Applications in Speech Processing; Recent Trends in Speech and NLP; Emerging trends in Speech Processing; Advances in Computational Linguistics and NLP.
Part II: Recent Trends in Machine Learning and Deep Learning; Analysis using Hybrid technologies with Artificial Intelligence; Exploring New Horizons in Computer Vision Research; Applications of Machine Learning and Deep Learning.
