Subject description - A2M31RAT

Summary of Study | Summary of Branches | All Subject Groups | All Subjects | List of Roles | Explanatory Notes               Instructions
A2M31RAT Speech technology in telecommunications Extent of teaching:2P+2C
Guarantors:  Roles:PO,V Language of
teaching:
CS
Teachers:  Completion:Z,ZK
Responsible Department:13131 Credits:6 Semester:L

Anotation:

The subject is devoted to basis of speech processing addressed to students of master program with special focus on communication applications as speech technology has currently many applications in communication systems. Further information can be found at http://noel.feld.cvut.cz/vyu/a2m31rat . Detailed information for registered students can be found at teaching portal http://moodle.kme.feld.cvut.cz .

Study targets:

The goals of the subject is to introduce used speech technology in the most important communication applications. Students should manage the knowledge as basic characteristics of speech signal, speech coding, speech enhancement, speech recognition, speech synthesis, etc. Students will practice basic tasks of speech processing in MATLAB environment and also other publicly available tools for speech analysis will be used. As a homework, students will elaborate semester project which will be presented at the exercise according to planned schedule.

Course outlines:

1. Introduction - speech signal, basic characteristics, speech production model
2. Digitalization and basic coding strategies (PCM, ADPCM, a-law)
3. Spectral characteristics of speech signal (DFT a LPC spectrum, LSF a LSP)
4. Vocoders used in telecommunications (RPE-LTP, CELP, ACELP)
5. Methods of noise suppression for speech signals (channel and acoustic noises, VAD)
6. Echo cancellation in speech signal
7. Measurement of speech quality (subjective and objective methods)
8. Principles of speech recognition: basic tasks, feature extraction, DTW algorithm
9. Small vocabulary recognizer based on HMM (HTK toolkit)
10. Speaker recognition: verification and identification.
11. Speech synthesis - basic principles (concatenative and formant synthesis, PSOLA)
12. Voice controlled dialogue communication systems
13. Packet loss concealment for speech transmitted via communication channel
14. Further application of speech processing in communication systems. Reserve

Exercises outline:

1. Introduction: speech signal, tools for analysis, sources of speech signals
2. Basic time-domain characteristics: energy, intensity, zero-crossing, fundamental frequency
3. Spectral characteristics: short-time DFT and LPC spectrum, spectrogram
4. LPC based vocoder: implementation of particular functional blacks
5. Suppression of additive noise in speech signal
6. Echo cancellation
7. Cepstrum and cepstral distance: voice activity detection, features for recognition
8. DTW based recognition: simple recognizer of particular words
9. HMM based recognition: basic tasks and demonstration of HMM modelling
10. Speaker verification based on GMM
11. Speech synthesis: implementation of formant synthesis, demonstration of available tools
12. Semester work presentations
13. Semester work presentations
14. Reserve. Credits

Literature:

[1] Huang, X. - Acero, A. - Hon, H.-W.: Spoken Language Processing. Prentice Hall 2001.

Requirements:

Bases of digital signal processing are supposed as preliminary knowledge.

Webpage:

https://moodle.fel.cvut.cz/course/view.php?id=540

Keywords:

speech processing, speech recognition, speech enhancement, speech coding, speech synthesis

Subject is included into these academic programs:

Program Branch Role Recommended semester
MPIB Common courses V
MPEEM1 Technological Systems V 3
MPEEM5 Economy and Management of Electrical Engineering V 3
MPEEM4 Economy and Management of Power Engineering V 3
MPEEM3 Electrical Power Engineering V 3
MPEEM2 Electrical Machines, Apparatus and Drives V 3
MPKYR4 Aerospace Systems V 3
MPKME4 Networks of Electronic Communication PO 3
MPKYR1 Robotics V 3
MPKYR3 Systems and Control V 3
MPKYR2 Sensors and Instrumentation V 3


Page updated 6.12.2019 17:52:32, semester: Z,L/2020-1, L/2018-9, Z,L/2019-20, Send comments about the content to the Administrators of the Academic Programs Proposal and Realization: I. Halaška (K336), J. Novák (K336)