During this hybrid lecture, Arjan van Hessen, researcher language and speech technology, will talk about the possibilities of using Automatic Speech Recognition (ASR). He will explain the (im)possibilities of the current speech recognizers, how ASR works and what will (hopefully) change in the coming months.

Automatic Speech Recognition – having spoken language recognized and processed by a computer – can be a very interesting technique for several disciplines. This lecture is aimed at humanities staff, but anyone for whom ASR can be a useful tool – for example to unlock oral history interviews, transcribe interviews, subtitle materials, etc. – is welcome.

* There has been a change of location: this lecture will now take place entirely online. *

Follow-up workshops

After this lecture, two follow-up workshops will be organized in which participants can apply speech recognition to their own material. Van Hessen will then discuss the available tools that you can use to achieve an optimal result. During the workshop, Whisper, an open-source speech recognition toolkit from OpenAI, will be used. The language to be recognized can be set as desired. The language of the workshop is English (unless everyone speaks Dutch).