Text and Speech Analysis for BE Anna University R21CBCS (V, VI (Vertical I - CSE/IT/CSE(AI&ML)/AI&DS/CS&BS - CCS369))

Syllabus Text and Speech Analysis - (CCS369) UNIT I NATURAL LANGUAGE BASICS Foundations of natural language processing - Language Syntax and Structure - Text Preprocessing and Wrangling - Text tokenization - Stemming - Lemmatization - Removing stop-words - Feature Engineering for Text representation - Bag of Words model - Bag of N-Grams model - TF-IDF model. Suggested Activities : • Flipped classroom on NLP. • Implementation of Text Preprocessing using NLTK. • Implementation of TF-IDF models. Suggested Evaluation Methods : • Quiz on NLP Basics. • Demonstration of Programs. (Chapter - 1) UNIT II TEXT CLASSIFICATION Vector Semantics and Embeddings - Word Embeddings - Word2Vec model - Glove model - FastText model - Overview of Deep Learning models - RNN - Transformers - Overview of Text summarization and Topic Models Suggested Activities : • Flipped classroom on Feature extraction of documents. • Implementation of SVM models for text classification. • External learning : Text summarization and Topic models. Suggested Evaluation Methods : • Assignment on above topics. • Quiz on RNN, Transformers. • Implementing NLP with RNN and Transformers. (Chapter - 2) UNIT III QUESTION ANSWERING AND DIALOGUE SYSTEMS Information retrieval - IR-based question answering - knowledge-based question answering - language models for QA - classic QA models - chatbots - Design of dialogue systems - evaluating dialogue systems. Suggested Activities : • Flipped classroom on language models for QA. • Developing a knowledge - based question-answering system. • Classic QA model development. Suggested Evaluation Methods : • Assignment on the above topics. • Quiz on knowledge-based question answering system. • Development of simple chatbots. (Chapter - 3) UNIT IV TEXT-TO-SPEECH SYNTHESIS Overview. Text normalization. Letter-to-sound. Prosody, Evaluation. Signal processing - Concatenative and parametric approaches, WaveNet and other deep learning-based TTS systems. Suggested Activities : • Flipped classroom on Speech signal processing. • Exploring Text normalization. • Data collection. • Implementation of TTS systems. Suggested Evaluation Methods : • Assignment on the above topics. • Quiz on wavenet, deep learning-based TTS systems. • Finding accuracy with different TTS systems. (Chapter - 4) UNIT V AUTOMATIC SPEECH RECOGNITION Speech recognition : Acoustic modelling - Feature Extraction - HMM, HMM-DNN systems. Suggested Activities : • Flipped classroom on Speech recognition. • Exploring Feature extraction. Suggested Evaluation Methods : • Assignment on the above topics. • Quiz on acoustic modelling. (Chapter - 5)

Read More