|Lecturers:||Prof. Dr.-Ing. Walter Kellermann|
Dr.-Ing. Heinrich Löllmann
M.Sc. Christian Hümmer
|Credit Points:||2,5 ECTS|
All data marked with a * are directly imported from UnivIS
Topic: Machine Learning for Acoustic Signal Processing
The field of machine learning is concerned with the construction of intelligent systems based on the automatic discovery of regularities in data. In the learning phase, an algorithm “learns” patterns from a set of training data by adapting its model parameters. The pretrained system is subsequently employed to analyze various input data. One prominent example of machine learning research is the task of automatic speech recognition, where the parameters of an acoustical model are estimated in a training phase and subsequently employed to recognize speech signals.
In the last two decades, a variety of approaches have been proposed applying machine learning techniques to classical signal processing tasks. This seminar focuses on the description of fundamental concepts from machine learning theory as well as their application to speech signal processing.
The seminar is open to German as well as foreign students. Therefore, all meetings and presentations will be held in English and the reports are expected to be written in English.