Time Line of the Lecture "Pattern Recognition and Machine Learning"

  • Structure of a (basic) neural network
  • Applications of neural networks
  • Types of neural networks
  • Basic training of neural networks
  • Example applications

Slides of the lecture

  • Basics of speaker verification und speaker identification
    • Preprocessing and segmentation
    • Codebook-based schemes
    • Schemes based on Gaussian mixture models
    • Model adaption
    • Discriminative approaches
  • Fundamentals of speech recognition
    • Speech recognition and understanding
    • Applications and system variants
    • Evaluation
  • Statistical speech recognition
    • Maximum a-posteriori (MAP) rule
    • Model simplification
    • Modeling
  • Conclusion and outlook

Slides of the lecture

  • Motivation
  • Fundamentals
    • The „hidden“ part of the model
    • The inner family of random processes
  • Fundamental problems of Hidden Markov Models
    • Efficient calculation of sequence probabilities
    • Efficient calculation of the most probable sequence

Slides of the lecture

  • Motivation
  • Fundamentals
    • Gaussian mixture models in practice
    • Generation of Gaussian mixture models
  • Applications in speech and audio processing
    • Bandwidth extension
    • Signal separation
    • Speaker recognition

Slides of the lecture

  • Motivation
  • System concept
  • Extension of the excitation signal
    • Spectral shifting and modulation
    • Non-linear characteristics
  • Extension of the spectral envelope
    • Approaches using neural networks
    • Codebook-based approaches
    • Linear mapping
  • Examples

Slides of the lecture

  • Motivation
  • Application examples
  • Cost function for the training of a codebook
  • LBG- and k-means algorithm
    • Basic schemes
    • Extensions
  • Combination with additional mapping schemes

Slides of the lecture

  • Introduction
  • Features for speech and speaker recognition
    • Fundamental frequency
    • Spectral envelope
  • Representation of the spectral envelope
    • Predictor coefficients
    • Cepstral coefficients
    • Mel-filtered cepstral coefficients

Slides of the lecture

  • Introduction
  • Characteristic of multi-microphone systems
  • Delay-and-sum structures
  • Filter-and-sum structures
  • Interference compensation
  • Audio examples and results
  • Outlook on postfilter structures

Slides of the lecture

  • Generation and properties of speech signals
  • Wiener filter
  • Frequency-domain solution
  • Extensions of the gain rule
  • Extensions of the entire framework
  • Empirical mode decomposition

Slides of the lecture

Website News

07.08.2019: Talk from Juan Rafael Orozco-Arroyave added.

11.07.2019: First free KiRAT version released - a game for Parkinson patients

25.06.2019: About 30 pupils from the Isarnwohld-Schule in Gettorf visited us.

02.05.2019: Christin Baasch finished sucessfully her defense on the evaluation of Parkinson speech.

30.11.2018: New student project on driver distraction added.

Recent Publications


J. Reermann, E. Elzenheimer and G. Schmidt: Real-time Biomagnetic Signal Processing for Uncooled Magnetometers in Cardiology, IEEE Sensors Journal, Volume 15, Number 10, Pages 4237-4249, June 2019, doi: 10.1109/JSEN.2019.2893236


Prof. Dr.-Ing. Gerhard Schmidt

E-Mail: gus@tf.uni-kiel.de

Christian-Albrechts-Universität zu Kiel
Faculty of Engineering
Institute for Electrical Engineering and Information Engineering
Digital Signal Processing and System Theory

Kaiserstr. 2
24143 Kiel, Germany

How to find us

Recent News

TensorFlow and Escape Rooms

The last two days (Monday and Tuesday, September 16 and 17, 2019), the whole DSS team did a course on TensorFlow and Keras. Since we already have interfaces of TensorFlow to our real-time tool KiRAT, it was time now to extend our knowledge on graphs and the corresponding training of weights, biases, etc. After two days of hard work we booked two escape rooms and solved the "secrets" hidden in ...

Read more ...