Algoritmy zpracování signálů

Přednášející:

Cvičící:

Předmět zajišťuje:

katedra teorie obvodů

Anotace:

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/ae2m31rat . Detailed information for registered students can be found at teaching portal http://moodle.kme.feld.cvut.cz .

Požadavky:

Bases of digital signal processing are supposed as preliminary knowledge.

Osnova přednášek:

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

Osnova cvičení:

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

Cíle studia:

Studijní materiály:

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

Poznámka:

Další informace:

Pro tento předmět se rozvrh nepřipravuje

Předmět je součástí následujících studijních plánů:

• Elektronika - elektronické systémy- strukturované studium (povinný předmět)