|
Instructors: Prof. Dr. Christian Biemann; Prof. Dr. Timo Florian Gerkmann
Event type:
Seminar
Displayed in timetable as:
Sem Spracherk.
Hours per week:
2
Credits:
3,0
Language of instruction:
German/English
Min. | Max. participants:
- | 20
Registration group: Anmeldegruppe Seminare ab WS 2015/16
Comments/contents:
In this seminar, we address all aspects of automatic speech recognition, i.e. the recognition and transcription of spoken language. This starts on signal level, where we extract and process features and signals in order to achieve a high robustness with respect to noise and speaker variations. Apart from robust approaches to training we will also cover the recognition of phonemes and words, up to automatic correction on the basis of natural language semantics.
Students present selected topics in order to achieve an overview on relevant techniques in the area of speech recognition.
Learning objectives:
In this seminar, students learn
- reception and critical acclaim of research papers
- presentation techniques
- theory of automatic speech recognition
- aspects of machine learning
- aspects of signal processing
- aspects of language technology
Didactic concept:
After a general introduction to the goals and structure of the seminar, we will distribute topics to participants. Every participant will be presenting one of the topics on automatic speech recognition. We expect active participation in the subsequent discussions. At the end of the seminar period, we expect a short summary paper.
Literature:
individually assigned per topic
Additional examination information:
To successfully pass, we ask the following
- seminar presentation on one topic in automatic peech recognition
- summary paper
- active participation in the discussions
|
