Page tree
Skip to end of metadata
Go to start of metadata


 Preface
Part A: Basic theory and methodology

  1. Introduction
    1. Why speech processing?
    2. Speech production and acoustic properties
    3. Phonetics (Wikipedia)
    4. Linguistics (Wikipedia)
    5. Speech perception (Wikipedia)
    6. Speech-Language pathology (Wikipedia)
  2. Characterization and basic tools for speech signals
    1. Waveform
    2. Windowing
    3. Spectrogram and the STFT
  3. Feature extraction for speech signals
    1. Pre-emphasis
    2. Autocorrelation and autocovariance
    3. Cepstrum and MFCC
    4. Linear prediction
    5. Fundamental frequency (F0)
    6. Zero-crossing rate
    7. Deltas and Delta-deltas
    8. PSOLA
  4. Machine learning for speech processing

    Part B: Applications

  5. Automatic speech recognition
    1. Standard methods
    2. End-to-end methods
  6. Speech synthesis
    1. Articulatory
    2. Concatenative
    3. Statistical
  7. Speaker recognition and verification
    1. Recognition
    2. Verification
  8. Speech coding and transmission
  9. Enhancement and bandwidth extension
    1. Speech enhancement
    2. Bandwidth extension
  10. Voice and speaking style conversion
    1. Voice conversion
    2. Speaking style conversion
  11. Speech analysis
    1. VAD → bit arbitrary place, but is there better?
    2. GIF
    3. F0
    4. Formants
  12. Paralinguistic applications
  13. Medical applications of speech processing
  14. Computational modelling of language acquisition

    Part C: Evaluation methods

  15. Intelligibility
    1. Objective
    2. Subjective
  16. Classification tasks
  17. Detection tasks



  • No labels