ELEC-E5500 - Speech Processing, 07.09.2020-19.10.2020

Topic outline

• Materials
  • 

    Module 1 - Introduction File

    Pdf-tiedosto

    Not available unless: You belong to any group
  • 

    Module 2 - Short-time analysis File

    Pdf-tiedosto

    Not available unless: You belong to any group
  • 

    Module 3 - Short-time processing File

    Pdf-tiedosto

    Not available unless: You belong to any group
  • 

    Module 4 - Classic DSP File

    Pdf-tiedosto

    Not available unless: You belong to any group
  • 

    Module 5 - Time-domain File

    Pdf-tiedosto

    Not available unless: You belong to any group
  • 

    Module 6 - Fundamental frequency File

    Pdf-tiedosto

    Not available unless: You belong to any group
  • 

    Module 7 - Voice Activity Detection File

    Pdf-tiedosto

    Not available unless: You belong to any group
  • 

    Module 8 - Speech Production File

    Pdf-tiedosto

    Not available unless: You belong to any group
  • 

    Module 9 - Speech Production Modelling File

    Pdf-tiedosto

    Not available unless: You belong to any group
  • 

    Guest lecture by Abraham Zewoudie - Part 1: Speaker recognition File

    Pdf-tiedosto

    Not available unless: You belong to any group
  • 

    Guest lecture by Abraham Zewoudie - Part 2: Speaker diarization File

    Pdf-tiedosto

    Not available unless: You belong to any group
  • 

    Guest lecture by Jarmo Malinen: Computational modelling of speech File

    Pdf-tiedosto

    Not available unless: You belong to any group
  • 

    Module 10 - Speech enhancement File

    Arkisto (ZIP)

    Not available unless: You belong to any group

    Jupyter lab notebooks for topic "Speech enhancement".

    Required packages: python3, jupter, jupyterlab, numpy, scipy, sounddevice (with pip), matplotlib

    Tested with fresh installation of anaconda (10/2020).
    

  • 

    Module 11 - Speech coding (time-domain) File

    Pdf-tiedosto

    Not available unless: You belong to any group
  • 

    Module 12 - Speech and audio coding (frequency-domain) File

    Pdf-tiedosto

    Not available unless: You belong to any group
  • 

    Module 13 - Quality Evaluation File

    Pdf-tiedosto

    Not available unless: You belong to any group
  • 

    Module 17 - Privacy and Security in Speech Technology File

    Pdf-tiedosto
  • 

    Supplemental material: Rabiner & Schaffer "Speech processing" File

    Pdf-tiedosto

    Not available unless: You belong to any group