Machine Learning for Speech and Audio Processing (New!)

The new lecture "Machine Learning for Speech and Audio Processing (MLSAP)" addresses especially students of the Master's program "Electrical Engineering, Information Technology and Computer Engineering". Starting in the summer term 2019, the course is curricularly anchored in the ELECTIVE module catalogues of the majors "Communications Engineering" (COMM), "Computer Engineering" (COMP), and "Systems and Automation" (SYAT).

In this one term lecture the fundamental methods of machine learning with applications to problems in speech and audio signal processing are presented:

• Fundamentals of Classification and Estimation
  • Basic Problems of Classification
  • Feature Extraction Techniques
  • Basic Classification Schemes
• Probabilistic Models
  • Stochastic Processes and Models
  • Gaussian Mixture Models (GMMs)
  • Hidden Markov Models (HMMs)
  • Training Methods
  • Bayesian Probability Theory: Classification and Estimation
  • Particle Filter
• Non-Negative Matrix Factorization (NMF)
  • Dictionary-based concept
• Neural Network and Deep Learning
  • Feed-Forward Neural Networks
  • Fundamental Applications
  • Learning Strategies: Supervised vs Unsupervised vs Reinforcement Learning
  • Training of Synaptic Weights: Backpropagation and Stochastic Gradient Descent
  • Behavior of Learning and the “Magic” of Setting Hyper‐Parameters
  • Generative Networks as a Complement to Directed Graphs
  • From „Shallow“ to „Deep“: Trade Comprehensibility for Performance
  • Specific Network Architectures
  • Applications in Signal Processsing
  • Interpretations and Realizations

Exercises are offered to gain a deeper understanding on the basis of practical examples.

The results of the evaluation are summarized below.

Participants of the evaluation: 12
Global grade: 1,3

Lecture
Concept of the lecture: 1,2
Instruction and behaviour: 1,3

Exercise:
Concept of the exercise: 1,5
Instruction and behaviour: 1,3

MLSAP_Vorlesung_Uebung_SS18.pdf