Ceska verze teto stranky Back to main page

BE2M31ZRE - Speech processing - Seminars
Summer semester 2023/2024

Tools for practical exercises:

  1. Tu - 20.2.2024 - Introduction: speech signals, analysis tools
    - interactive work with signals in the environment of MATLAB, Praat, Wavesurfer
    - recording of database for further work during the semester
    Guidelines for the seminar
    Task to be delivered (5 POINTS) - till Fr 1.3.2024 10:00, see Tak No.1 - Delivery of minidatabes with recorded utterances for details.

  2. Tu - 27.2.2024 - Basic time- and frequency-domain characteristics
    - Energy, power, intensity, RMS value
    - Zero-crossing rate
    - Spectrogram and filter-bank spectrum
    Guidelines for the seminar

  3. Tu - 5.3.2024 - Pitch estimation
    - Pitch estimation from autocorrelation function
    - Necessary pre-processing and post-processing
    - Estimation within MATLAB and Praat (Wavesurfer)
    Guidelines for the seminar

  4. Tu - 12.3.2024 - LPC spectrum and formant estimation
    - computation of LPC spectrum (spectrogram)
    - formant estimation from AR model (LPC parameters)
    - Estimation within MATLAB and Praat (Wavesurfer)
    Guidelines for the seminar

  5. Tu - 19.3.2024 - LPC vocoder: MATLAB implementation of principles parts - checked homework (5 POINTS)
    - AR model of speech signal
    - elementary vocoder with error signal exication
    - quantization within error-excited vocoder (RELP simulation)
    - vocoder with atificially generated exication
    Guidelines for the seminar

  6. Tu - 26.3.2024 - Cepstrum, cepstral distance and voice activity detection
    - DFT, LPC, and MFCC cepstrum
    - Cepstrum of longer speech utterance
    - Energy-based and cepstral based voice activity detection
    Guidelines for the seminar

  7. Tu - 2.4.2024 - DTW-based speech recognition
    - computation of distance matrix
    - looking for the optimal path through given distance matrix
    - simple recognizer of isolated digits
    Guidelines for the seminar

  8. Tu - 9.4.2024 - Basics of classification based on GMM and VQ - checked homework (5 POINTS)
    - principles of GMM and VQ
    - the recognition of vowels based on formants or cepstrum
    Guidelines for the seminar

  9. Tu - 16.4.2024 - HMM-based recognition I
    - Recognition of vowel sequence
    - Computation of GMM for particular states
    - Emitted probability in selected states
    Guidelines for the seminar

  10. Tu - 23.4.2024 - HMM-based recognition II
    - Emitted probability in all states
    - Transient probabilities
    - Passing through HMM, Viterbi decoding, optimum path
    Guidelines for the seminar

  11. Tu - 30.4.2024 - Speaker verification on the basis of VQ and GMM - checked homework (5 POINTS)
    - cepstrum distribution for given speaker, differences among speakers
    - creation of speaker codebook and GMM model
    - realization cross verification from available database
    - interactive on-line verification
    Guidelines for the seminar

  12. Tu - 7.5.2024 - Speaker identification on the basis of GMM
    - GMM based speaker verification (a simple modification of the task from last seminar)
    - usage of extended feature vector
    - search of selected speaker within a set of unknown utterances
    Guidelines for the seminar

    Tu - 14.5.2024 - Cancelled - RECTOR'S DAY

  13. Tu - 21.5.2024 - SEMESTER TEST (20 POINTS) + Speech synthesis