Daylong data: Raw audio to transcript via automated & manual open-science tools

Several of the central questions in language, social cognition, and developmental research focus on the roles of input, output, and interaction on learning and communication. While it has become easy to collect long-form recordings, getting useful data out of them is a more daunting task. Across four mini-sessions, this tutorial aims to address pre- and post-data collection concerns, and provide a hands-on introduction to manual and automated annotation techniques. Attendees will leave this tutorial with resources and concrete experience for collecting, annotating, and sharing/archiving naturalistic recordings, including specific open-science practices relevant for these data.

Duke Scholars

Author Elika Bergelson Psychology & Neuroscience