Conference Program / Wissenschaftliches Programm
| Time | Wednesday (March 4) | Thursday (March 5) | Friday (March 6) |
|---|---|---|---|
| Morning | Arrival | 9:00–10:00 Keynote 2: Thomas Haigh |
9:30–10:30 Keynote 4: Hans Rudolf Straub |
| 10:20–11:40 Session 3: Speech Synthesis |
10:50–12:10 Session 5: Voice, Language and Cognition |
||
| Noon | 11:30–12:30 Registration 12:30–13:00 Welcome |
11:40–12:40 Mittag in der Mensa 12:40 Fototermin (...) |
12:10 Best Student Paper Award Closing Remarks 12:30 Farewell |
| Afternoon | 13:00–14:00 Keynote 1: Rüdiger Hoffmann |
13:00–14:40 Stadtführungen |
Departure |
| 14:20–15:40 Session 1: Speech Signal Recognition and Enhancement |
15:00–16:00 Keynote 3: Thomas Hoffmann |
||
| 16:00–17:20 Session 2: Speech Analysis I |
16:20–17:20 Session 4: Speech Analysis II |
||
| Evening | 17:30 Reception (Sommerresidenz, Holzer-Saal) |
17:40-18:40 Show & Tell Poster Session |
|
| 19:00 ESSV Business Meeting (at Café im Paradeis) |
19:00 Conference Dinner at GUTMANN |
The detailed programm may still change slightly.
Keynotes
Rüdiger Hoffmann:
Über den Versuch, ein totgesagtes Pferd zu reiten.
Sprachtechnologie in der DDR im zeitlichen und räumlichen Kontext
Thomas Haigh:
Is speech recognition “artificial intelligence”?
A historical examination of academic branding.
Thomas Hoffmann:
Constructions, Computation and Creativity:
How different is LLM and human linguistic creativity?
Hans Rudolf Straub:
Formale Semantik im offenen semantischen Raum
Talks / Fachvorträge
Wednesday (5 March) / Mittwoch (5. März)
Keynote 1: Rüdiger Hoffmann
Session 1: Speech Signal Recognition and Enhancement
Chair: to be announced
- Abdullah al Foysal, Ronald Böck:
Enhancing ASR for German Medical Domain without Fine-Tuning - Nilesh Madhu:
Iterative Ambient-Signal-Aware Speech Enhancement via Cascaded DNN Processing without Retraining - Lisa Winkler, Andreas Wendemuth:
An Approach to Improving Robustness in Dynamic Acoustic Environments: Context Noise Representation Learning from Urban Speech Emotion Recognition - Sophie Hoppe, Anabell Hacker, Markus Brückl:
Im Raum der Täuschung - Raumhall als Schwachstelle automatischer Deepfake-Erkennung
Session 2: Speech Analysis I
Chair: to be announced
- Marcella Palladino:
Zur Transkription mündlicher Phänomene in der politischen Sprache - Jürgen Trouvain:
Dialektale Vielfalt in visuellen und auditiven Illustrationen: „Nordwind und Sonne“ in saarländischen Dialekten - Neda Mousavi, Felix Burkhardt:
The Emotional Portrayal of an Ordinary Talk - Daniel Duran, Robert Fromont, Jennifer Hay, Allie Osborne, Melanie Weirich, Miriam Oschkinat, Stefanie Jannedy:
Evaluating Full Automation of Computational Sociophonetics for the Plapper Corpus
Thursday (March 5) / Donnerstag (5. März)
Keynote 2: Thomas Haigh
Session 3: Speech Synthesis
Chair: to be announced
- Yamini Sinha, Ingo Siegert
From Writing to Speaking: on the Limits of Text-Trained Authorship Models for Speech Transcripts - Ian Howard:
A Servo-Motor-Actuated Artifical Lung for Robotic Speech Production - Tianyi Zhang, Peter Birkholz:
Joint Estimation of Source and Filter Parameters for Speaker Adaptation in Articulatory Speech Synthesis - Paul Kontantin Krug, Christoph Wagner, Peter Birkholz, Timo Stich:
TensorTract3: Pushing the Limits of Articulatory Speech Synthesis
Keynote 3: Thomas Hoffmann
Session 4: Speech Analysis II
Chair: to be announced
- Daniel Duran, Laurens Winkler, Sina Zarrieß:
How well can LLMs handle novel phonetic forms? - Eugenia Rykova, Tanja Rinker, Angela Grimm:
ASR-based Automatic Assessment of Oral Production Tasks in Multilingual Children - Niklas Berensmeyer, Stefan Hillmann, Wolfgang Maier:
Measuring User Acceptance of Proactively Played Touristic Texts in an In-Car Voice Assistant
Show & Tell - Session
Posters
Friday (March 6) / Freitag (6. März)
Keynote 4: Hans Rudolf Straub
Session 5: Voice, Language and Cognition
Chair: to be announced
- Matthias Busch, Jonas Schewior, Andreas Wendemuth, Ingo Siegert:
Creating Documents with Voice: Maybe it is not about Transcription but Reflection? - Moinam Chatterjee, Behnam Ensan, Andreas Wendemuth, Ayoub Al-Hamadi:
Think Like a Team: Graph-based Representation of Shared Mental Models in Human-Agent Collaboration - Ronald Römer, Johannes F. Kuhn, Markus Huber-Liebl, Peter b. Graben, Matthias Wolff:
Ein konzeptioneller Beitrag zur Entwicklung und Nachbildung von Problemlöse- und Sprachfähigkeiten - Stefan Hillmann, Philipp Harnisch, Daniel Schuhmann, Navid Ashrafi, Jan-Niklas Voigt-Antons:
A Modular Multimodal Dialog Architecture for Digital PROM Collection
Posters
- P1 Harald Höge:
Towards a Brain-Computer Interface Modelling the Phonological Short-Term Memory - P2 Syed Hur Abbas, Peter Birkholz, Muhammad Arif:
Feature-Enhanced Consensus Graph Model for EEG-based Imagined Word Recognition - P3 Marcella Palladino, Gannuscio Vincenzo:
Außerparlamentarische politische Kommunikation: Datenerhebung und Analyseperspektiven - P4 Anabell Hacker, Iris Sidonie Bakker, Ingo Siegert:
Evaluation of WebRTC as a Framework for Voice Recordings in Online Surveys - P5 Martha Schubert, Valentin Kany:
Automatic Detection of Disfluencies in L1 and L2 Child Speech - P6 Sven Grawunder, Ute Gradmann:
Assessing Speaking Modes in Radio News Using Topic Classification and Acoustic Parameters - P7 Zihao Huang, Tianyi Zhang, Peter Birkholz:
Self-Supervised Multi-Task Learning for Enhanced Prosody Prediction in German Articulatory Speech Synthesis - P8 Robin Bitterlich, Paul Böhm, Oliver Jokisch:
Parameter Optimization for Administration-Specific Speech Transcription with the Faster Whisper System
Show & Tell
- S1 Thomas Ranzenberger, Steffen Fresinger, Tobias Bocklet, Korbinian Riedhammer:
HAnS: Multimodal RAG-based Persona Generation for Media and Documents in E-Learning - S2 Felix Gräßer, Robert Wardenga, Dominik Jülg, Christian Gaida, Rico Petrick:
Alphaspeech Transcribe – eine autonome, containerisierte Speech-to-Text-Plattform für professionelle Transkriptions- und Dokumentationsworkflows