Lecture "Pattern Recognition and Machine Learning"


Basic Information
Lecturers: Gerhard Schmidt (lecture) and Tobias Hübschen, Bastian Kaulen (exercise)
Room: online until further notice
Language: English
Target group: Students in electrical engineering and computer engineering
Prerequisites: Basics in system theory

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
    • Learning types
      • Unsupervised learning
      • Supervised learning
      • Reinformcement learning
    • Codebooks
    • Gaussian mixture models (GMMs)
    • Artificial Neural Networks (ANNs)
      • Multilayer perceptron
      • Convolutional neuronal networks (CNNs)
      • Recurrent neural networks (RNNs)
      • Autoencoder networks
      • Generative adversarial networks (GANs)
    • Hidden Markov models (HMMs)
  • Selected applications of machine learning



Due to the current rising Covid-19 numbers, lecture and exercise will be held online starting Nov. 23. 

A preliminary lecture and exercise schedule for WS 21/21 is now available.

The lecture will be given in seminar room F/SR-I and can be attended according to the university's current rules. Until further notice, the lecture will, additionally, be live streamed via zoom. The link will be provided through the corresponding Olat course.

There are two student talk sessions, one in December and one in January. For the first session please sign up no later than 09.12.2021. For the second session please sign up until 16.01.22. Giving the talk is a requirement to sit the exam. More information can be found below.

Remember to register for the exam in the QiS system. Without such a registration we will have to cancel any exam slot you booked with us. Booking of exam slots is possible here.



The following schedule regarding lectures and excercises is preliminary and may be adapted during the semester. The lecture will usually take place from 14:00 h - 16:30 h.

Date Lecture Exercise
26.10.2021 Introduction -
02.11.2021 Noise Suppression + Beamforming Noise Suppression (video)
09.11.2021 Beamforming + Feature Extractiom Beamforming (video)
16.11.2021 Feature Extraction + Codebook Training Feature Extraction (video)
23.11.2021 Codebook Training + Bandwidth Extension Codebook Training (video)
30.11.2021 Bandwidth Extension Bandwidth Extension (video) + Question time with content per request (start time will be communicated)
07.12.2021 Gaussian Mixture Models Gaussian Mixture Models (video)
14.12.2021 Student Talks Student talks
11.01.2022 Neural Networks Neural Networks (video)
18.01.2022 Hidden Markov Models Hidden Markov Models (video)
25.01.2022 Student Talks Student talks
01.02.2022 Speaker and Speech Recognition Question time + content per request (start time will be approx. 16:00 h), Speaker and Speech Recognition (video)


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 "Neural networks"
(Network types, training procecures)
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)


Matlab Demos

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



For each lecture topic an on-demand video will be provided. On 30.11.2021 and on 01.02.2022 there will be an in-presence exercise to discuss your questions and requested topics. You may send in questions (if you want the answer to be supported by slides) or exercise topic suggestions to This email address is being protected from spambots. You need JavaScript enabled to view it. at any time. Both exercise sessions can be viewed using the lecture's zoom link.

Video Content Material

Noise suppression:

  • Wiener Filter summary
  • comprehension questions
  • python demo


  • beamforming summary
  • comprehension questions
  • python demo

Feature extraction:

  • linear prediction
  • LPC, LPCC, MFCC features
  • comprehension questions
  • python demo

Codebook training:

  • codebooks
  • codebook training
  • comprehension questions
  • python demo

Bandwidth extension:

  • bandwidth extension summary
  • comprehension questions
  • python demo

Gaussian Mixture Models:

  • Gaussian Mixture Models
  • EM algorithm
  • comprehension questions
  • python demo

Neural Networks:

  • neural networks summary
  • comprehension questions
  • python demo

Hidden Markov Models:

  • hidden markov models summary
  • comprehension questions
  • python demo

Speaker and Speech Recognition:

  • speaker and speech recognition summary
  • comprehension questions
  • python demo



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. For the first and the second talk session, the talk registration deadlines are 09.12.2021 and 16.01.2022, respectively.

Below you can find the preliminary schedule of the talks.

Date Room Time Topic Presenter(s)
14.12.2021 zoom 14:05 h A Scalable Framework for Multiple Speaker Localization and Tracking Arthur Lepsien
14.12.2021 zoom 14:20 h Interpretability Methods for Deep Neural Networks in Medical Image Analysis Moritz Boueke
14.12.2021 zoom 14:35 h Data Mining in Healthcare Applications Golam Sarowar Jahan Rifat
14.12.2021 zoom 14:50 h Generative Adverserial Networks Henrik Horst
14.12.2021 zoom 15:05 h Face Recognition Based on Deep Learning Karoline Gussow
14.12.2021 zoom 15:20 h break  
25.01.2022 zoom 14:05 h Support Vector Machines Tim Johannisson
25.01.2022 zoom 14:20 h Decision Tree and Random Forest Piotr Smietana
25.01.2022 zoom 14:35 h Feedforward Neural Networks Abidur Rahman
25.01.2022 zoom 14:50 h Speaker Localization using Beamforming Klara Görnig
25.01.2022 zoom 15:05 h Character Recognition using Machine Learning Patricia Fuchs
25.01.2022 zoom 15:20 h break  
25.01.2022 zoom 15:30 h k-Nearest-Neighbor Simulator for Weather Variables Simon Hesselbrock
25.01.2022 zoom 15:45 h Music Chord Recognition based on Neural Networks Jan-Niklas Busse
25.01.2022 zoom 16:05 h Deep Learning for Video Game Playing Marco Driesen
25.01.2022 zoom 16:20 h Gesture Recognition using Hidden Markov Models Konstantinos Karatziotis
25.01.2022 zoom 16:35 h Cryptocurrencies Price Prediction using Machine Learning Mohammadmahdi Asrar
25.01.2022 zoom 16:50 h break  
25.01.2022 zoom 17:00 h Edge Detection: Signal Processing vs. Neural Networks Finn Bathel
25.01.2022 zoom 17:15 h Machine Learning based Failure Management in Optical Communications Leon Neidhardt
25.01.2022 zoom 17:30 h Signature Recognition using Machine Learning Wajid Ali
25.01.2022 zoom 17:45 h Singing Voice Separation from Monaural Recordings Nico Töppe
25.01.2022 zoom 18:00 h Neural Networks for Speaker Separation Finn Röhrdanz
25.01.2022 zoom 18:15 h Next-Generation Machine Learning for Biological Networks Torben Niklas Lundt



Current evaluation Completed evaluations