Speech and Language Processing - Module 4F11
Module LecturersProf. Phil Woodland firstname.lastname@example.org and Dr. Bill Byrne email@example.com
Introduction & Applications. Speech production mechanisms, types of speech sound, source-filter model, applications of speech and text processing.
Lecture notes available in [lect1.pdf].
FFT based methods. All-pole filter models, calculation of LP coefficients. LP Spectrum. Cepstral analysis. Front-end analysis for speech recognition (MFCCs).
Lecture notes available in [lect23.pdf]
Statistical speech recognition, task complexity. Hidden Markov models. Continuous density HMM parameter estimation, Baum-Welch algorithm, Viterbi algorithm, Gaussian mixture models for HMMs.
Lecture notes available in [lect45.pdf]
Large vocabulary speech recogntion, continuous speech training, limitations of word models, context dependent phones, parameter tying, WSJ performance.
Lecture notes available in [lect6.pdf]
Perplexity, N-gram language models, discounting, interpolation.
Lecture notes available in [lect7.pdf]
Continuous speech recognition. Pruning. Integrating context dependent HMMs and N-gram language models.
Lecture notes available in [lect8.pdf]
Efficient realization of probabilistic models for sequence processing. Transduction, composition, determinization, minimum-cost search. WFSTs in ASR search and other language processing applications.
Lecture notes available in [lect9-10.pdf]
Statistical pattern processing approaches to translation. Automatic evaluation of translation quality.
Lecture notes available in [lect11.pdf]
Parallel text as training data. Models of word and phrase alignment in translation. Model estimation procedures.
Lecture notes available in [lect12.pdf]
Phrase-based translation systems. Implementation via WFSTs.
Lecture notes available in [lect13.pdf]
Introduction to TTS.
Lecture notes available in [lect14.pdf]
Examples papersThere will be two examples papers and two examples classes for the course. The solutions to the examples papers will be available on-line (after examples classes).
Examples Paper 1 available in [egPaper1.pdf].
Solutions to examples paper 1 available in [egPaper1soln.pdf]
Examples Paper 2 available in [examplepaper2.pdf]
Solutions to examples paper 2 available in [examplepaper2_solns.pdf]
Exam FormatAssessment by 1.5 hour exam: 3 questions from 4.