Teaching


Courses Taught

Previous Courses

Studieren ab 50

Students, Interns and other Advisees:

I have advised more than 40 degree theses (BSc, MSc, Diploma), many of which lead to publications:

@Inproceedings{SchmidtSiegertESSV:2021, Title = {Studie zur Lösbarkeit des Problems starker Pegelschwankungen im Home-Entertainment}, Address = {Berlin, Germany}, Author = {Schmidt, Georg and Siegert, Ingo}, Booktitle = {Elektronische Sprachsignalverarbeitung 2021. Tagungsband der 32. Konferenz}, Pages = {303--310}, Year = {2021}, series = {Studientexte zur Sprachkommunikation}, publisher = {TUDpress}, volume = {99}, keywords={kongressbook,kongress} }

@INPROCEEDINGS{9211896, author={{Böhm},Felix and {Siegert}, Ingo and {Belyaev}, Alexander and {Diedrich},Christian}, booktitle={2020 25th IEEE International Conference on Emerging Technologies and Factory Automation (ETFA)}, title={An Analysis of the Applicability of VoiceXML as Basis for a Dialog Control Flow in Industrial Interaction Management}, year={2020}, pages={30-37}, doi={10.1109/ETFA46521.2020.9211896}, keywords={conferencebook,conference} } @Inproceedings{KuzhipathalilITG:2020, author = {Kuzhipathalil, Adarsh and Thomas, Anto and Chand, Keerthana and Siegert, Ingo}, title = {Intelligent LSF-answering system -- an Alexa Skill}, booktitle = {Sprachassistenten - Anwendungen, Implikationen, Entwicklungen : ITG-Workshop : Magdeburg, 3. März, 2020}, year = {2020}, pages = {39}, notes= {Abstract}, keywords={other} }

@Inbook{10.1007/978-3-030-60276-5_50, author={Siegert, Ingo and Sinha, Yamini and Jokisch, Oliver and Wendemuth, Andreas}, editor={Karpov, Alexey and Potapova, Rodmonga}, title={Recognition Performance of Selected Speech Recognition APIs -- A Longitudinal Study}, booktitle={Speech and Computer}, year={2020}, publisher={Springer International Publishing}, address={Cham}, pages={520--529}, abstract={Within the last five years, the availability and usability of interactive voice assistants have grown. Thereby, the development benefits mostly from the rapidly increased cloud-based speech recognition systems. Furthermore many cloud-based services, such as Google Speech API, IBM Watson, and Wit.ai, can be used for personal applications and transcription tasks. As these tasks vary in their domain, their complexity as well as in their interlocutor, it is challenging to select a suitable cloud-based speech recognition service. As the update-process of online-services can be completely handled in the back-end, client applications do not need to be updated and thus improved accuracies can be expected within certain periods. This paper contributes to the field of automatic speech recognition, by comparing the performance of speech recognition between the above-mentioned cloud-based systems on German samples of high-qualitative spontaneous human-directed and device-directed speech as well as noisy device-directed speech over a period of eight months.}, isbn={978-3-030-60276-5}, keywords={conferencebook,conference} }

@INPROCEEDINGS{9209538, author={{Weißkirchen}, Norman and Vasudeva Reddy, Mainampati and {Wendemuth}, Andreas and {Siegert}, Ingo}, booktitle={2020 IEEE International Conference on Human-Machine Systems (ICHMS)}, title={Utilizing Computer Vision Algorithms to Detect and Describe Local Features in Images for Emotion Recognition from Speech}, year={2020}, pages={1-6}, doi={10.1109/ICHMS49158.2020.9209538}, keywords={conferencebook,conference} }