In the humanities, many fields deal with large amounts of spoken language: oral history, sociology, ethnology, linguistics, phonetics, and many more. In this workshop we give a systematic introduction into the complexity of processing spoken language data, ranging from recording via transcription to the analysis of the data. We will focus on two key aspects: a) where and to what extend can we make use of automatic processing, e.g. by using speech recognition for transcription, and b) how can we access the rich information contained in the speech signal itself to gain new insights, e.g. emotion detection.
- Week 1: will give an introduction to the field, present technical solutions for speech recordings and then show how modern technology can be used to create a basic transcript of oral data.
- Week 2: will focus on extending the basic transcript by an in-depth analysis of the literal content and the speech signal itself. Finally, we will outline how to integrate one’s data into sustainable and reusable data archives.
The course is a hands-on workshop, with many exercises and the opportunity to work with one’s own data.