The third in a series of AI Discovery Sessions for Information, Intelligent Machines, and New Knowledge, featuring AI Studio Experiments.Using Topic Modeling to Describe 19th Century NovelsRebecca Wingfield, Arcadia Falcone, Javier de la Rosa, Scott BaileyIn 2011, Stanford acquired a collection of single-volume 19th century novels. Since these novels are not widely held in major research libraries, there is only minimal descriptive information about them. This project explores topic modeling to enhance subject access to the collection.Automating Audio TranscriptionJosh Schneider, DeBauche and Sarav ShahThis team has been using Google's Cloud Speech-to-Text tool to automate the transcription of audio recordings from the Library's Special Collections and University Archives including the Allen Ginsberg papers and KZSU Project South interviews. They will share their experience and results.Lowering the bar to making CloudVision data usable by leveraging IIIFJessie Keck, Jack Reed, and Chris BeerIIIF makes accessing images as easy as constructing a URL. Google CloudVision makes running images through AI based image analysis relatively easy as well. Our project aims to leverage the data returned from CloudVision in a way that will allow IIIF based viewers to be able to consume the image analysis data using existing open standards.Image Recognition for Archaeological ResearchClaudia Engel and Justine IssaviAfter 25 years of research, the Çatalhöyük Archaeological Project has accumulated about 150,000 images. The metadata are incomplete or inconsistent and researchers are often interested in information that is not captured at all. Using AI helps image tagging and archaeological object recognition.Similar Image Search: How Machine Learning Can Assist with Metadata CreationHilary ThorsenMachine learning has allowed significant advances to be made with visual search giving metadata librarians new possibilities for automating and improving metadata creation workflows.