BAMU · Third Year B.E./B.Tech Computer Science and Engineering · NEP 2020
Speech & Language Processing
PECT-2 · Elective III · Semester VI · 3 credits · CIA 40 + SEE 60
One of the Elective III options.
Module 1: Origins and Challenges of NLP; Word-Level Analysis
15 hoursGrammar-based and statistical language modelling, regular expressions, finite-state automata, English morphology and transducers, tokenisation, spelling correction and minimum edit distance; n-grams, smoothing, interpolation and backoff, word classes and rule-based, stochastic and transformation-based POS tagging, HMM and maximum-entropy models.
Examined in the 60-mark end-semester paper
- Natural language processing and its challenges
- Morphological analysis and finite-state transducers
- Tokenisation, stemming and lemmatisation
- Spelling correction and minimum edit distance
- N-gram language models and smoothing
- Part-of-speech tagging
- HMM tagging and the Viterbi algorithm
- Maximum entropy and CRF taggers
Module 2: Syntactic Analysis; Semantics and Pragmatics
15 hoursCFGs and treebanks for English, dependency grammar, syntactic and shallow parsing, dynamic-programming and probabilistic CYK parsing, lexicalised PCFGs and feature structures; first-order and description logics, syntax-driven semantic analysis, word senses, thematic roles, word-sense disambiguation and word similarity.
Examined in the 60-mark end-semester paper
- Syntactic parsing and probabilistic CFGs
- Treebanks and universal dependencies
- CYK and Earley parsers
- Lexical semantics and WordNet
- Word sense disambiguation
Module 3: Basic Concepts of Speech Processing; Speech Analysis and Modelling
15 hoursArticulatory and acoustic phonetics and speech production, the short-time Fourier transform, filter-bank and LPC methods; speech features and distortion measures, cepstral distances, LPC, PLP and MFCC coefficients, dynamic time warping, and HMMs with Viterbi search and Baum–Welch re-estimation.
Examined in the 60-mark end-semester paper
- Speech production and phonetics
- Short-time Fourier, filter-bank and LPC analysis
- Speech features: LPC, PLP and MFCC
- Speech distortion measures and dynamic time warping
- HMMs for speech: Viterbi and Baum–Welch
Module contents are summarised from the official BAMU syllabus . AiCanCode.org is not affiliated with Dr. Babasaheb Ambedkar Marathwada University (BAMU).