Module also offered within study programmes:
General information:
Name:
Speech Processing
Course of study:
2017/2018
Code:
IES-1-706-s
Faculty of:
Computer Science, Electronics and Telecommunications
Study level:
First-cycle studies
Specialty:
-
Field of study:
Electronics and Telecommunications
Semester:
7
Profile of education:
Academic (A)
Lecture language:
English
Form and type of study:
Full-time studies
Responsible teacher:
dr inż. Ziółko Bartosz (bziolko@agh.edu.pl)
Academic teachers:
dr inż. Gałka Jakub (jgalka@agh.edu.pl)
Module summary

Description of learning outcomes for module
MLO code Student after module completion has the knowledge/ knows how to/is able to Connections with FLO Method of learning outcomes verification (form of completion)
Skills
M_U001 Student can programme basic speech recognition applications. ES1A_U08 Completion of laboratory classes
M_U002 Student can programme basic speech analysis application. ES1A_U08 Completion of laboratory classes
M_U003 Student can programme basic speech synthesiser. ES1A_U08 Completion of laboratory classes
Knowledge
M_W001 Student knows basics of speech technologies ES1A_W01, ES1A_W20, ES1A_W21 Completion of laboratory classes
FLO matrix in relation to forms of classes
MLO code Student after module completion has the knowledge/ knows how to/is able to Form of classes
Lecture
Audit. classes
Lab. classes
Project classes
Conv. seminar
Seminar classes
Pract. classes
Zaj. terenowe
Zaj. warsztatowe
Others
E-learning
Skills
M_U001 Student can programme basic speech recognition applications. - - + - - - - - - - -
M_U002 Student can programme basic speech analysis application. - - + - - - - - - - -
M_U003 Student can programme basic speech synthesiser. - - + - - - - - - - -
Knowledge
M_W001 Student knows basics of speech technologies + - - - - - - - - - -
Module content
Lectures:

Introduction and general scheme of ASR.
Speech and language resources available for automatic speech recognition.
Bayes Rule, Maximum A-posteriori Probability (MAP).
Speech parameterisation and segmentation (mel frequency cepstral coefficients (MFCC), perceptual linear predictive analysis (PLP)).
Speech modelling (hidden Markov model (HMM), artificial neural networks (ANN)).
Decoding, Vitterbi algorithm
Dictionaries in computer systems, Levenshtein metric
Grammar modelling (parsers, n-grams, part of speech taggers).
Semantic modelling (bag-of-words, wordnet, vector space model).

Laboratory classes:

Developing speech processing applications based on available toolkits.

Student workload (ECTS credits balance)
Student activity form Student workload
Summary student workload 82 h
Module ECTS credits 3 ECTS
Realization of independently performed tasks 15 h
Participation in lectures 28 h
Participation in laboratory classes 14 h
Preparation for classes 20 h
Preparation of a report, presentation, written work, etc. 5 h
Additional information
Method of calculating the final grade:

Based on work at laboratory

Prerequisites and additional requirements:

Signal Processing

Recommended literature and teaching resources:

D. Jurafsky, J. H. Martin, SPEECH and LANGUAGE PROCESSING. An Introduction to Natural Language Processing, Computational Linguistics, and Speech Recognition Second Edition”, Pearson Prentice Hall, 2008
L. R. Rabiner, A Tutorial on Hidden Markov Models and Selected Applications in Speech Recognition PDF
HMM w MIT, week #5, lecture #10: www.ocw.mit.edu
http://class.coursera.org/nlp
http://ocw.mit.edu/courses/electrical-engineering-and-computer-science/6-345-automatic-speech-recognition-spring-2003/
http://nlp.ipipan.waw.pl/wiki/clip

Scientific publications of module course instructors related to the topic of the module:

http://www.dsp.agh.edu.pl/pl:publications

Additional information:

None