PROGRAM SPEECH TECH DAY 2026

Theme: Crossing the Lines: Academia, Industry, and the Future of Knowledge

Under construction

Program:

Session I Keynote

09:30 - 10:00 Walk-in
10.00 - 10:05 Welcome by Roeland Ordelman (Stichting Open Spraaktechnologie)
10:05 - 11:00 Sound or silence?  (Dr. Ir. David van Leeuwen, Radboud University & Spraaklab)

11:00 - 11:30 Coffee break

Session II  

11:30 - 12:45 (Chair: Matt Coler)

• A Comparative Look at Industry and Academic Research (Aki Kunikoshi, ReadSpeaker)

• Project FRIS: Creating a Multi-Speaker, Multi-Dialect Frisian Speech Dataset for Robust ASR  (Tessel Wisman, Juvoly)

• Automated medical notes with Autoscriber: from idea to validated tool (Martijn Bauer, Autoscriber)

• The HOSAN project (Roeland Ordelman & Xiyuan Gao)

13:00 - 13:45 Lunch

Session III 

13:45 - 15:20 (Chair: Odette Scharenborg)

• From Data Abundance to Care Insights:  An AI-Based Approach for Quality of Care in Long-Term Care (Sil Aarts, U Maastricht)

• Development of a child-friendly, clinical tool to objectively measure speech motor control in children who stutter (Lottie Stipdonk, Erasmus MC)

• Speech technology in the classroom: using prosodic speech analysis to optimize inclusive adaptive fact learning systems (Thomas Wilschut, RUG)

15:20 - 15:45 Short coffee break

15:45 - 16:15

• Panel Discussion "Bridging the gap between academia and industry" (Moderator: Henk van den Heuvel)

Panelists:

• Sil Aarts (U Maastricht)

• David van Leeuwen (Radboud University & Spraaklab)

• Dorota Iskra (TransPerfect)

• Shekhar Nayak (RUG, Campus Fryslân)

Session IV Posters and information market

16:15 - 17:00 Coffee & visit the posters and information market

Posters:

• Mariia Zamyrova (Radboud University): Prompting Whisper for Joint Speech Transcription and Diarization

• Keara Schaaij (Radboud University): Exploring alignment strategies for large language model response generation in spoken dialogue 

• Roeland Ordelman (University of Twente) & Henk van den Heuvel (Radboud University): The HOSAN project, picturing ASR for Dutch

• Marianne de Heer Kloots (University of Amsterdam): What do self-supervised speech models learn about Dutch? Probing for linguistic structure in Wav2Vec2-NL and HuiBERT

• Gaofei Shen (Tilburg University): Probing in the reverse direction

• Cecilia Kuan (Radboud University): Audio dialogue synthesis of Dutch medical dialogues

• Maxime Verwoert (Maastricht University), Loes van Bemmel (Maastricht University), Frits M.E. Franssen (Maastricht University, Maastricht University Medical Center, Ciro), Sami O. Simons (Maastricht University, Ciro): Listening for COPD: Voice as a Digital Biomarker for COPD Identification

Information Market:

• Reson8 Labs B.V. (Thomas Kluiters, Anna Lantink) 

• Talksom (Tijs Zwinkels, Jeroen Naeff) 

• Visio & Stichting OVOS (Timon van Hasselt, Peter Steenbergen)

16:45 - 18:00 Drinks