Sidebar Menu

Lecture "Pattern Recognition and Machine Learning"

 

Basic Information

 
 
Lecture overview  
  Lecturers:   Gerhard Schmidt (lecture) and Tobias Hübschen (exercise)  
  Room:   F-SR-I  
  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
  • Feature extraction and data compression
  • Pattern recognition and data regression
    • Codebooks
    • Gaussian mixture models (GMMs)
    • Artificial Neural Networks (ANNs)
    • Hidden Markov models (HMMs)
  • Selected applications of machine learning
 

 

News

According to the rules of our university, currently all exams of this lecture will be postponed due to COVID-19. As soon as we have a solution we will inform those of you who already booked an exam via e-mail.

Starting this winter semester, the exercise will be extended by practical tasks such as training a neural network using Python and TensorFlow.  For this practical part of the excercise you are recommended to bring your own laptop. The exercise will be conducted as blocks, the schedule can be found below.

 

Schedule

The following schedule regarding lectures and excercises is preliminary and may be adapted during the semester. Each date refers to the time slot from 13:00 h until 16:30 h.

 
 
Date   Content  
  22.10.2019   Introduction  
  29.10.2019   Noise Suppression + Beamforming (part 1)  
  05.11.2019   Beamforming (part 2) + exercise  
  12.11.2019   Feature Extraction + Codebooks (part 1)  
  19.11.2019   Codebooks (part 2) + Bandwidth Extension  
  26.11.2019   Exercise  
  03.12.2019   Gaussian Mixture Models + Neural Networks (part 1)  
  10.12.2019   Neural Networks (part 2) + exercise  
  17.12.2019   Exercise  
  07.01.2020   Hidden Markov Models  
  14.01.2020   Speaker and Speech Recognition + exercise  
  21.01.2020   Exercise  
  28.01.2020   Student Talks  

 

Lecture Slides

 
 
Link   Content  
    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

 
 
Link   Content  
    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.

 
 
Link   Content  
      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.

 
 
Date   Room   Time   Topic   Presenter(s)  
  28.01.2020   F-SR I   13:05 h   Random Forests   Bastian Schroeter  
  28.01.2020   F-SR I   13:20 h   Transfer Learning   Kristina Apelt  
  28.01.2020   F-SR I   13:35 h   Reinforcement Learning   Daniaal Dar  
  28.01.2020   F-SR I   13:50 h   Transformer Models   Sönke Bartels  
  28.01.2020   F-SR I   14:05 h   Face Recognition   Yasin Akbaba  
  28.01.2020   F-SR I   14:30 h   Biological Pattern Recognition   Jannek Winter  
  28.01.2020   F-SR I   14:45 h   Self Learning   Tim Schmidt  
  28.01.2020   F-SR I   15:00 h   Vehicular Crash Detection using Hidden Markov Models   Toni Lekic  
  28.01.2020   F-SR I   15:15 h   Convolutional Neural Networks   Hussein Al-Nedjefi  
  28.01.2020   F-SR I   15:30 h   Speech Enhancement using a Microphone Array Mounted on an Unmanned Aerial Vehicle   Alexander Staffa  

 

 

Programs and Data

Please enter the password to see the content

 

Evaluations

 
 
Link   Content   Link   Content  
    Current evaluation     Completed evaluations