Summer Workshop
Summer workshops will take place at the Faculty of Information Technology, June 23th - August 1st 2025.
Topics & Research Groups
- Play your Part: Towards LLM role-playing agents that stick to their role
- Advancing Expert-Level Reasoning and Understanding in Large Audio Language Models
- End to End multi channel multi talker ASR, EMMA
- TTS4ALL: TTS in low resource scenarios: data management, methodology, models, evaluation
Program
Workshop (June 23rd - August 1st 2025)
Research teams will work on selected topics.
Opening Day (June 23rd 2025)
Presentations will be live-streamed via YouTube.
All times below are local time in Brno, Czech Republic.
Opening Remarks — FIT, Brno University of Technology, Room E112
| 08:00 | bus departure from BUT dorms (Kolejní 2, Brno) to venue (Bozetechova 2/1, Brno) |
| 08:15 | Continental Breakfast (FIT BUT E103 respirium) |
| 09:00 | Call to Order (Honza Černocký) |
| 09:05 | Welcome Remarks (BUT rector, FIT BUT representative) |
| 09:10 | How We Got Here: History of the summer workshops (Sanjeev Khudanpur) |
Summary of Workshop Objectives and Teams
| 09:30 | EMMA: End-to-end multi-channel multi-talker ASR (Lukáš Burget) |
| 09:55 | Discussion and Q&A |
| 10:00 | Play Your Part: LLM role-playing agents that stick to their role (Ricard Marxer) |
| 10:25 | Discussion and Q&A |
| 10:30 | Break |
| 10:45 | AuGI: Towards audio general intelligence (Ramani Duraiswami) |
| 11:10 | Discussion and Q&A |
| 11:15 | TTS4ALL: TTS in low resource scenarios (Yannick Estève) |
| 11:40 | Discussion and Q&A |
| 11:45 | JSALT 2025 Organizational Information (Honza Černocký) |
| 12:00 | Adjourn to Workshop Laboratory |
Workshop Laboratory Setup — FIT Main Building
| 12:10 | Walk-through of JSALT Labs (Assemble @ security/reception desk on 0th floor) |
| 12:30 | Adjourn for Lunch (on your own) |
| 14:00 |
Welcome Picnic — FIT BUT E103 respirium
| 17:30 | Cocktail Reception |
| 18:00 | Picnic Dinner (RSVP to jsalt2025@jhu.edu) |
Plenary Lectures
Expected 1x week.
- Plenary lecture 1 Fri June 27, 11:00, Room E112, Marc Delcroix: Neural Target Speech and Sound Extraction: An Overview
- Plenary lecture 2 Tue July 1, 11:00, Room E112, Barbara Schuppler: Cross-layer models for conversational speech recognition in low-resourced scenarios
- Plenary lecture 3 Thu July 10, 11:00, Room E112, Ramani Duraiswami: Differentiable Modeling for Machine Learning
- Plenary lecture 4 Tue July 15, 11:00, Room E112, Loïc Barrault: Large Concept Model: beyond token-based Large Language Models
- Plenary lecture 5 Fri July 18, 11:00, Room E112, Hervé Bredin: Speaker diarization, a
loveloss story - Plenary lecture 6 Tue July 22, 11:00, Room E112, Xavier Serra: Methodologies for Music Understanding and Generation in the Context of Trustworthy AI
- Plenary lecture 7 Thu July 24, 11:00, Room E112, Jordan Boyd-Graber Ying: Helpful AI Models: You can't always get what you want, but you might get what you need
Closing Presentations (July 31st - August 1st 2025)
Program/presentations will be published here.
You might also be interested in previous workshops.
