FI:PV158 Speech signal processing - Course Information
PV158 Speech signal processing
Faculty of InformaticsSpring 2008
- Extent and Intensity
- 2/1. 3 credit(s) (plus extra credits for completion). Recommended Type of Completion: zk (examination). Other types of completion: k (colloquium), z (credit).
- Teacher(s)
- doc. Dr. Ing. Jan Černocký (lecturer), doc. RNDr. Ivan Kopeček, CSc. (deputy)
- Guaranteed by
- prof. Ing. Václav Přenosil, CSc.
Department of Machine Learning and Data Processing – Faculty of Informatics
Contact Person: doc. RNDr. Ivan Kopeček, CSc. - Timetable
- Thu 8:00–9:50 B411, Thu 10:00–10:50 B117
- Prerequisites (in Czech)
- Výuka probíhá na FIT VUT dle rozvrhu http://www.fit.vutbr.cz/study/course-l.php?id=6007.
- Course Enrolment Limitations
- The course is also offered to the students of the fields other than those the course is directly associated with.
- fields of study / plans the course is directly associated with
- Applied Informatics (programme FI, B-AP)
- Applied Informatics (programme FI, N-AP)
- Information Technology Security (programme FI, N-IN)
- Bioinformatics (programme FI, B-AP)
- Bioinformatics (programme FI, N-AP)
- Information Systems (programme FI, N-IN)
- Informatics with another discipline (programme FI, B-BI)
- Informatics with another discipline (programme FI, B-FY)
- Informatics with another discipline (programme FI, B-GE)
- Informatics with another discipline (programme FI, B-GK)
- Informatics with another discipline (programme FI, B-CH)
- Informatics with another discipline (programme FI, B-IO)
- Informatics with another discipline (programme FI, B-MA)
- Informatics with another discipline (programme FI, B-SO)
- Informatics with another discipline (programme FI, B-TV)
- Informatics (programme FI, B-IN)
- Informatics (programme FI, M-IN)
- Informatics (programme FI, N-IN)
- Mathematical Informatics (programme FI, B-IN)
- Parallel and Distributed Systems (programme FI, B-IN)
- Parallel and Distributed Systems (programme FI, N-IN)
- Computer Graphics and Image Processing (programme FI, B-IN)
- Computer Graphics (programme FI, N-IN)
- Computer Networks and Communication (programme FI, B-IN)
- Computer Networks and Communication (programme FI, N-IN)
- Computer Systems and Data Processing (programme FI, B-IN)
- Computer Systems (programme FI, N-IN)
- Embedded Systems (eng.) (programme FI, N-IN)
- Programmable Technical Structures (programme FI, B-IN)
- Theoretical Informatics (programme FI, N-IN)
- Upper Secondary School Teacher Training in Informatics (programme FI, M-SS)
- Upper Secondary School Teacher Training in Informatics (programme FI, M-TV)
- Upper Secondary School Teacher Training in Informatics (programme FI, N-SS) (2)
- Artificial Intelligence and Natural Language Processing (programme FI, B-IN)
- Artificial Intelligence and Natural Language Processing (programme FI, N-IN)
- Image Processing (programme FI, N-AP)
- Course objectives
- Applications of speech processing, digital processing of speech signals, production and perception of speech, introduction to phonetics, pre-processing and basic parameters of speech, linear-predictive model, cepstrum, fundamental frequency estimation, coding - time domain and vocoders, recognition - DTW and HMM
- Syllabus
- Informational contents of written and spoken form of speech.
- Techniques of signal processing applied to speech: Fourier transform, z-transform, linear filtering.
- Time domain and frequency domain behavoir of linear systems.
- Signal processing model of speech production.
- Excitation and filter.
- Determination of parameters using linear prediction.
- LPC coefficients and derived parameters (PARCOR, LAR,...).
- Speech analysis using short-time Fourier transform (STFT): filter-bank interpretation, computation using fast Fourier transform (FFT).
- Cepstral analysis.
- Parameterization with perceptually warped frequency axis.
- Fundamental frequency determination.
- Features for speech processing, criteria of choice.
- Measures of similarity between speech segments.
- Speech coding: waveform and parametric vocoders.
- Excitation modeling (CELP).
- Phonetic vocoders.
- Speech recognition: Hidden Markov Models (HMM).
- HMM training and HMM decoding.
- Extension of HMMs to continuous speech recognition.
- Statistical language models.
- The studied methods are experimentally exercised in computer laboratories (Matlab).
- Literature
- Assessment methods (in Czech)
- Výuka: týdně 2h přednáška, 1x 14 dní 2h počítačových cvičení Matlab.
Podmínky pro ukončení kursu: zápočet - úspěšně absolvovaný test v posledním počítačovém cvičení, kolokvium - úspěšně absolvovaný test v posledním počítačovém cvičení A odevzdaný a presentovaný domácí projekt, zkouška - úspěšně absolvovaný test v posledním počítačovém cvičení A odevzdaný a presentovaný domácí projekt A písemná zkouška.
test v počítačovém cvičení - několik jednoduchých příkladů v Matlabu, k disposici libovolné poznámky, literatura, všechny vytvořené funkce. Max. 20 bodů ke zkoušce.
domácí projekt - na výběr z témat na http://www.fit.vutbr.cz/~cernocky/speech/projekty.html registrace během celého semestru, krátká písemná zpráva (4 strany A4), může být i ručně psaná, ústní presentace (10 min.) na poslední přednášce. Max. 20 bodů ke zkoušce.
písemná zkouška - k disposici veškerá literatura a výpočtní technika, . 2 hodiny, 5 teoretických otázek, 5 početních příkladů, po 6 bodech. Max. 60 bodů.
Hodnocení v případě ukončení zkouškou: celkem 100 bodů: 0-39 bodů: 4, 40-59 bodů: 3, 60-79 bodů: 2, 80-100 bodů: 1 - Language of instruction
- Czech
- Further Comments
- The course is taught annually.
- Teacher's information
- http://www.fit.vutbr.cz/~cernocky/speech
- Enrolment Statistics (recent)
- Permalink: https://is.muni.cz/course/fi/spring2008/PV158