Lecture "Pattern Recognition"

Basic Information

Lecturers:   Gerhard Schmidt (lecture) and Christin Baasch (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)
    • 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

No news yet!

 

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 "Speaker recocnition"
(Basics, codebook-based schemes, GMM-based schemes)
  Slides of the lecture "Hidden Markov Models (HMMs)"
(Training, efficient probability estimation)
  Slides of the lecture "Speech Recognition"
(Application of HMMs, speech dialog systems)

 

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.

de en    
  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 "Speaker recognition"
  Questionnaire for the lecture "Hidden Markov Models"
  Questionnaire for the lecture "Speech recognition"

 

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 an adaptive filter-related topic that interests you, and to improve your presentational skills. The talks should take ten minutes, plus 2.5 minutes of discussion and 2.5 minutes of feedback.

Below you can find the schedule of the talks.

Date   Room   Time   Topic   Presenter(s)
20.01.2017   F-SR-II   09:30 h   Pattern Recognition Techniques for Facial Recognition   Christin Willrodt
20.01.2017   F-SR-II   09:45 h   Iris Recognition   Charles Kaskas,
Jack Saud
20.01.2017   F-SR-II   10:10 h   Hyperspectral imaging   Christin Bald,
Katharina Rebbe
20.01.2017   F-SR-II   10:35 h   Emotion Recognition  

Arpita Kappattanavar,
Anubhav Jhalani

20.01.2017   F-SR-II   11:00 h   Closing   Gerhard Schmidt

 

Date   Room   Time   Topic   Presenter(s)
27.01.2017   F-SR-II   08:15 h   Opening   Gerhard Schmidt
27.01.2017   F-SR-II   08:20 h   Neural Networks   Bastian Biedermann,
Patrick Wiegand,
Eva Peschke
27.01.2017   F-SR-II   09:00 h   Convolutional Neural Networks   Tobias Klawonn,
Morten Stabenau
27.01.2017   F-SR-II   09:25 h   Google Picture Analysis and Creation   Dennis Niehusen
27.01.2017   F-SR-II   09:40 h   Investigations on the Use of Random Forests and Hough Forests for Landmark and Object Localization   Lennart Brünig
27.01.2017   F-SR-II   09:55 h   Pattern Recognition in Everyday Life   Sebastian Bossenz,
Moritz Weihs
27.01.2017   F-SR-II   10:20 h   Speech Analysis in Job Interview   Jan Reinhold
27.01.2017   F-SR-II   10:35 h   Fingerprint Recognition   Abdukader Kouja
27.01.2017   F-SR-II   10:50 h   Closing   Gerhard Schmidt

 

Date   Room   Time   Topic   Presenter(s)
03.02.2017   F-SR-II   08:15 h   Opening   Gerhard Schmidt
03.02.2017   F-SR-II   08:20 h   Pedestrian Recognition or Driving Assistance   Peter Lund
03.02.2017   F-SR-II   08:35 h   Xerox: The Risk of Pattern Recognition   Matz Simon
03.02.2017   F-SR-II   08:50 h   Pattern Recognition Approach to Diagnosis of Hyperthyroidism   Finn Spitz
03.02.2017   F-SR-II   09:05 h   Recognition of Partially Occluded Objects   Hannes Flieger
03.02.2017   F-SR-II   09:20 h   Machine Learning   Aditya Sondhi,
Simar Mann Singh Chawala
03.02.2017   F-SR-II   09:45 h   Self-Organizing Maps in Pattern Recognition   Nicolas Preinl
03.02.2017   F-SR-II   10:00 h   Quantitative Analysis of Nonverbal Communication for Competence Analysis   Vijender Bolla,
Vinod Devraj
03.02.2017   F-SR-II   10:25 h   Pattern Recognition in Medical Imaging   Alexander Wilbrandt,
Gabriel Bello Waldschütz
03.02.2017   F-SR-II   10:50 h   Gesture controlled Robot using image processing   Riya Joy,
Jerin Joseph Koshy
03.02.2017   F-SR-II   11:15 h   Abnormal Sound Recognition with Audio Feature Combination and modified GMM   Alok Sreenivas,
Shwetha Chandrashekara
03.02.2017   F-SR-II   11:40 h   Credit Card Fraud Detection Using Neural Network   Seedo Eldho Paul
03.02.2017   F-SR-II   11:55 h   A Robust Dissimilarity-Based Neural Network for Temporal Pattern Recognition   Govinda Chaithanya Kabbinahithilu
03.02.2017   F-SR-II   12:10 h   Closing   Gerhard Schmidt

 

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.

Date   Time   Students (matriculation numbers)   Assessor
10.02.2017   08:00 h   1029503, 1029560   Christin Baasch
10.02.2017   09:00 h   1010619, 1111029   Christin Baasch
10.02.2017   10:00 h   1010613, 1012825, 1010608   Christin Baasch
15.02.2017   08:00 h   1009267, 1006194, 1002324   Christin Baasch
15.02.2017   09:30 h   1016041   Christin Baasch
15.02.2017   10:00 h   1021298   Christin Baasch
15.02.2017   10:30 h   1016040   Christin Baasch
29.03.2017   11:00 h   1029544   Tobias Hübschen
30.03.2017   08:00 h   4276, 1006213, 1006230   Christin Baasch
30.03.2017   09:30 h   1029502, 1015858   Christin Baasch
30.03.2017   10:30 h   8852, 1006003   Christin Baasch
30.03.2017   11:30 h   994323   Christin Baasch
31.03.2017   08:00 h   1010633, 1012957   Christin Baasch
31.03.2017   09:00 h   1002064, 1002329, 1008371   Christin Baasch
31.03.2017   10:30 h   1011765, 1010623   Christin Baasch
31.03.2017   12:30 h   1015886, 1029504, 1015963   Christin Baasch
31.03.2017   14:00 h   1015885, 1029548, 1029545   Christin Baasch
31.03.2017   15:30 h   1015927, 1029547   Christin Baasch
31.03.2017   16:30 h   1020508   Christin Baasch
31.03.2017   17:00 h   1029472   Christin Baasch

 

Recent Publications

P. Durdaut, J. Reermann, S. Zabel, Ch. Kirchhof, E. Quandt, F. Faupel, G. Schmidt, R. Knöchel, and M. Höft: Modeling and Analysis of Noise Sources for Thin-Film Magnetoelectric Sensors Based on the Delta-E Effect, IEEE Transactions on Instrumentation and Measurement, published online, 2017

P. Durdaut, S. Salzer, J. Reermann, V. Röbisch, J. McCord, D. Meyners, E. Quandt, G. Schmidt, R. Knöchel, and M. Höft: Improved Magnetic Frequency Conversion Approach for Magnetoelectric Sensors, IEEE Sensors Letters, published online, 2017

 

Website News

18.06.2017: Page about KiRAT news added (also visible in KiRAT).

31.05.2017: Some pictures added.

23.04.2017: Time line for the lecture "Adaptive Filters" added.

13.04.2017: List of PhD theses added.

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

Alexej Namenas - A New Guy in the Team

In June Alexej Namenas started in the DSS Team. He will work on real-time tracking algorithms for SONAR applications. Alexej has done both theses (Bachelor and Master) with us. The Bachelor thesis in audio processing (beamforming) and the Master thesis in the medical field (real-time electro- and magnetocardiography). In addition, he has intership erperience in SONAR processing.

We are pretty ...


Read more ...