Lecture "Pattern Recognition and Machine Learning"

Basic Information

Lecturers:   Gerhard Schmidt (lecture) and Tobias Hübschen (exercise)
Room:   F-SR-II
Language:   English
Target group:   Students in electrical engineering and computer engineering
Prerequisites:   Basics in system theory
Contents:  

In this lecture the basics of speech, audio, and music signal processing are treated. Often schemes that are based on statistical optimization are utilized for these applications. The involved cost function are matched to the human audio perception.

Topic overview:

  • Preprocessing to reduce signal distortions
    • Noise reduction
    • Beamforming
  • Speech and speaker recognition
    • Fundamentals of speech generation
    • Feature extraction
    • Gaussian mixture models (GMMs)
    • Artificial Neural Networks (ANNs)
    • Hidden Markov models (HMMs)
    • Recognition of speech and speakers
  • Enhancement of signal playback
    • Extending the bandwidth of speech signals
    • Equalization of loudspeakers
    • Upmix of stereo signals for playback with more than two loudspeakers

 

News

The dates for the oral exams have been set. There are 6 dates available throughout February, March, and April.

 

Lecture Slides

 

  Slides of the lecture "Introduction"
(Introduction, boundary conditions of the lecture, applications)
  Slides of the lecture "Noise Suppression"
(Noise suppression, dereverberation, speech reconstruction)
  Slides of the lecture "Beamforming"
(Fixed and adaptive beamforming, postfiltering)
  Slides of the lecture "Feature Extraction"
(Linear prediction, cepstrum, mel-filtered cepstral coefficients)
  Slides of the lecture "Codebook Training"
(K-means algorithm, LBG algorithms)
  Slides of the lecture "Bandwidth Extension"
(Model-bases approaches, evaluation)
  Slides of the lecture "Gaussian Mixture Models (GMMs)"
(Training with the EM algorithm, applications)
  Slides of the lecture "Hidden Markov Models (HMMs)"
(Efficient probability calculation, training of HMMs)
  Slides of the lecture "Speaker and Speech Recognition"
(Application of GMMs and HMMs, speech dialog systems)
  Slides of the lecture "Neural networks"
(Network types, training procecures)

 

Matlab Demos

  Matlab demo (GUI based) for adaptive noise suppression
  Matlab demo (GUI based) for linear prediction

 

Exercises

Please note that the questionnaires will be uploaded every week before the excercises, if you download them earlier, you won't get the most recent version.

  Questionnaire for the lecture "Noise Suppression"
  Questionnaire for the lecture "Beamforming"
  Questionnaire for the lecture "Feature extraction"
  Questionnaire for the lecture "Codebook training"
  Questionnaire for the lecture "Bandwidth extension"
  Questionnaire for the lecture "Gaussian Mixture Models"
  Questionnaire for the lecture "Hidden Markov Models"
  Questionnaire for the lecture "Speaker and speech recognition"
  Questionnaire for the lecture "Neural Networks"

 

Talks

At the end of the semester, each student will give a talk about a certain topic. The aim is both to give you the chance to work on a pattern recognition-related topic that interests you, and to improve your presentational skills. The talk is also a prerequisite for your admission to the exam. The talks should be held in English and should take ten minutes, plus 2.5 minutes of discussion and 2.5 minutes of feedback. Please write an email to This email address is being protected from spambots. You need JavaScript enabled to view it. to reserve your topic.

Below you can find the schedule of the talks. The current plan is to start the talks on 01.02.2019 (and to continue on 08.02.2019).

Date   Room   Time   Topic   Presenter(s)
01.02.2019   F-SR II   08:20 h   Visual Pattern Recognition   Ayman Soukieh
01.02.2019   F-SR II   08:35 h   Linear Discriminant Classifiers   Jakob Sommer
01.02.2019   F-SR II   08:50 h   Convolutional Neural Networks   Julian Soudan
01.02.2019   F-SR II   09:05 h   Deep Learning   Tobias Seide
01.02.2019   F-SR II   09:25 h   Machine Translation using Neural Networks   Johannes Hoffmann
01.02.2019   F-SR II   09:40 h   Investigation on Bandwidth Extension for Speaker Recognition   P.S.S.N Sri Harsha
01.02.2019   F-SR II   09:55 h   Reservoir Computing for Speech Recognition   Erman Kalpakci
01.02.2019   F-SR II   10:10 h   Audio Classification using GMMs   Frederik Kühne
01.02.2019   F-SR II   10:30 h   Detection and Localization of Text from Images   Claudius Karnstädt
01.02.2019   F-SR II   10:45 h   Facial Recognition System   Shayan Ahmed
01.02.2019   F-SR II   11:00 h   Random Forest Algorithm   Simon Schrader
01.02.2019   F-SR II   11:15 h   Weakly Supervised Photo Enhancer for Digital Cameras   Marcel Reher

 

Exams

Below is the list of students with their exam dates. If you do not have a date for the exam yet please use the oral exam booking system on this website. You can find the booking system here.

Date   Time   Students (matriculation numbers)   Assessor
20.02.2019   08:00 h   1016013   Tobias Hübschen
20.02.2019   09:00 h   1126914   Tobias Hübschen
20.02.2019   10:30 h   1113624   Tobias Hübschen
20.02.2019   11:00 h   1140813   Tobias Hübschen
22.02.2019   09:30 h   1006677   Tobias Hübschen
22.02.2019   10:00 h   1010628   Tobias Hübschen
06.03.2019   10:00 h   6798   Tobias Hübschen
06.03.2019   11:00 h   1125413   Tobias Hübschen
01.04.2019   09:30 h   1030685   Tobias Hübschen
01.04.2019   10:00 h   1022054   Tobias Hübschen
03.04.2019   08:00 h   1023438, 1004958   Tobias Hübschen

 

Website News

30.11.2018: New student project on driver distraction added.

01.10.2018: Dissertation of Philipp Bulling added.

14.08.2018: New section about our SONAR "sisters" added.

18.07.2018: New section about our Parkinson voice training game added.

07.07.2018: New lecture Fundamentals of Acoustics by Jan Abshagen added.

Recent Publications

   

J. Reermann, E. Elzenheimer and G. Schmidt: Real-time Biomagnetic Signal Processing for Uncooled Magnetometers in Cardiology, IEEE Sensors Journal, January, 2019 (early access, doi:  10.1109/JSEN.2019.2893236)

Contact

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

Recent News

Saturday Morning Physics 2018

The DSS team was invited to participate in the last of the "Saturday Morning Physics" (SMP) events in 2018. On December 8th, a Saturday of course, Thorben Kaak, Gerhard Schmidt, and Owe Wisch gave a talk on underwater signal processing. Pupils from all around Schleswig-Holstein were quite interested, especially in the basics of SONAR systems.