Seminar "Selected Topics in Speech and Audio Signal Processing"


Basic Information
Lecturers: Gerhard Schmidt and group
Semester: Winter term
Language: English or German
Target group: Master students in electrical engineering and computer engineering
Prerequisites: Fundamentals in digital signal processing

If you want to sign up for this seminar, you need to register with the following information in the registration form

  • surname, first name,
  • e-mail address,
  • matriculation number,

Please note that the registration period starts 17.10.2022 at 10:00 h and ends 30.10.2022 at 23:59 h. All applications before and after this registration period will not be taken into account.

Registration will be possible within the before mentioned time under the following subsite - Seminar Registration.

During the registration process you will also choose your seminar topic. Only one student per topic is permitted (first come - first serve).

The registration is binding. A deregistration is only possible by sending an e-mail with your name and matriculation number to This email address is being protected from spambots. You need JavaScript enabled to view it. until Sunday, 30.10.2022 at 23:59 h. All later cancellations of registration will be considered as having failed the seminar.

Time: Preliminary meeting per arrangement with individual supervisor
Written report due on 06.02.2023
Final presentations, 16.03.2023 at 09:00 h

Students write a scientific report on a topic closely related to the current research of the DSS group. Potential topics, therefore, deal with digital signal processing related to medical signal processing.

Students will also present their findings in front of the other participants and the DSS group.


Topics for WS 22/23

Topic title Description
Acoustic Scene Analysis and Event Detection

Acoustic scene analysis (ASA) is the process of decomposing complicated input audio signals into auditory perceptual objects reflecting physical sources, or temporal acoustic patterns (such as music). It is important for applications such as elderly and newborn monitoring, surveillance, and multimedia retrieval. The goal of this seminar is to provide an overview of signal processing techniques for acoustic scene analysis and event detection including terminology, available data set, challenges and latest research directions.

Audio-visual speech recognition

While speaking, movements of the speaker´s lips (and other visible articulators) contains information. Seeing somebody speaking significantly improves our ability of understanding under noisy conditions. Using both modalities – auditory and visual - for feature extraction can improve several speech analysis tasks and also speech recognition. In this seminar, different approaches for visual speech recognition and feature extraction algorithms should be investigated. Therefore, advantages, disadvantages and limitations should be discussed. Eventually, you will outline what methods or features could be applied in the context of dysarthric speech and discuss challenges and differences in this context.