Conference Program / Wissenschaftliches Programm
| Time | Wednesday (5 March) | Thursday (6 March) | Friday (7 March) |
|---|---|---|---|
| Morning | Arrival | 9:00–10:00 Keynote 1: Pauline Larrouy-Maestri Making Sense of voices |
9:30–10:30 Keynote 2: Ines Bose Gesprochene Leichte Sprache |
| 10:10–11:30 Session 3: Recognition in HMI and Therapeutic Applications |
10:50–12:10 Session 6: Voice, Language and Cognition |
||
| Noon | 11:30–12:30 Registration 12:30–13:00 Welcome |
11:30–13:30 Mittag in der Mensa 13:00 Fototermin (Steintor Campus) |
12:10 Best Student Paper Award Closing Remarks 12:30 Farewell |
| Afternoon | 13:00–14:20 Session 1: Multimodal Perception of Speech and Non-verbal Cues |
13:30–14:50 Session 4: Benchmarking ASR and TTS |
13:00 Exploring Art, History & Culture in Halle |
| 14:45–16:15 Poster Session |
15:00–16:10 Show & Tell |
||
| 16:30–17:30 Session 2: Computational linguistics and LLM-related systems |
16:20–17:40 Session 5: Multilingual Speech and Language Data Processing |
Departure | |
| Evening | 17:30 Reception |
18:00 City ralley |
|
| 19:00 ESSV Business Meeting (at LÖZIUS) |
19:00 Dinner at KRUG ZUM GRÜNEN KRANZE |
The detailed programm may still change slightly.
Guidelines for talks and posters.
Conference Program (PDF). (updated 2025-03-05 7:00)
Keynotes
Pauline Larrouy-Maestri:
Making sense of voices
Ines Bose:
Gesprochene Leichte Sprache – barrierefrei, verständlich und akzeptabel?
Talks / Fachvorträge
Wednesday (5 March) / Mittwoch (5. März)
Session 1: Multimodal Perception of Speech and Non-verbal Cues
Chair: Judith Pietschmann
- Anabell Hacker:
"Auf die inneren Werte kommt es an"? – Relevanz von Stimme und Gesicht bei der Beurteilung von Attraktivität, Sympathie Und Persönlichkeit - Phrashant Khatri, Hansjörg Mixdorff, Preeti Rao, Albert Rilliard:
Recognition of audio-visual attitudes - Janniek Wester, Pauline Larrouy-Maestri:
Role of speech comprehension on the perception of humanness - Konstantin Sering:
Smiling PAULE
Posters
Session 2: Computational linguistics and LLM-related systems
Chair: Bernd Möbius
- Johannes Kuhn, Matthias Wolff, Isidor Konrad Maier:
Wortgenerator für minimalistische grammatiken - Md Monsur Ali, Abdullah Al Foysal, Siddarth Venkateswaran, Ronald Böck:
Structured review on rag- and multi-agent frameworks - Isidor Konrad Maier, Tillmann Rosenow, Okko Tuuri, Matthias Wolff:
Frequency-magnitude relation of numeral words based on search-engine results
Thursday (6 March) / Donnerstag (6. März)
Keynote 1: Pauline Larrouy-Maestri
Session 3: Recognition in HMI and Therapeutic Applications
Chair: Sven Grawunder
- Hans-Günter Hirsch, Yannic Tiggelkamp, Christian Neumann, Hendrike Frieg, Stefan Knecht:
Evaluating the user interface of the Rehalingo speech training system with aphasic patients - Arne-Lukas Fietkau, João Menezes, Peter Birkholz:
Evaluating optopalatography sensor positions for command word recognition - Sara Mühlhausen, Sarah Gomez, Norina Lauer, Timo Baumann:
Cross-lingual transfer learning to improve aphasic speech recognition - Daniel Duran, Leonie Schade, Joana Cholin, Petra Wagner:
Testing the strategic elicitation of creative pronunciations in monologues and dialogues
Show & Tell - Session
Session 4: Benchmarking ASR and TTS
Chair: Oliver Jokisch
- Raviteja Boddu, Anderson de Lima Luiz, Munir Georges, Thomas Ranzenberger, Korbinian Riedhammer:
Significance-based summarization for lecture recordings: a multi-modal perspective - Thomas Ranzenberger, Ilja Baumann, Sebastian P. Bayerl, Dominik Wagner, Tobias Bocklet, Korbinian Riedhammer:
Evaluation of recognition errors of hybrid and transformer-based ASR systems in German video lectures - Ivan Kraljevski, Frank Duckhorn, Daniel Sobe, Constanze Tschoepe, Matthias Wolff:
Speech-to-text in upper sorbian: current state - Christopher Gebauer, Lars Rumberg, Fabian Witt, Edith Beaulac, Hanna Ehlert, Jörn Ostermann:
Rule-based grammatical error detection on spontaneous children’s speech
Session 5: Multilingual Speech and Language Data Processing
Chair: Neda Mousavi
- Silvia Modena, Marcella Palladino, Vincenzo Gannuscio:
A multilingual corpus of German, French and Italian political discourse: goals and methodological challenges - Markus Brückl, Anabell Hacker, Nancy Wünderlich, Katrin Talke, Dalida Valeeva:
Eine Datenbank für Markensprechweise (branddb) - Christoph Draxler, Felicitas Kleber, Sven Grawunder, Jürgen Trouvain:
Teilautomatisierter Workflow zur Aufbereitung grosser Audiodatenmengen für Signalbasierte Analysen - Huiyu Liu, Gokul Srinivasagan, Munir Georges:
Real-time audio transcriber for language barrier-free classrooms
Friday (7 March) / Freitag (7. März)
Keynote 2: Ines Bose
Session 6: Voice, Language and Cognition
Chair: Jürgen Trouvain
- Oliver Niebuhr, Rongjie Shi, Wentao Gu:
Effects of loudness on timbre features: comparison of different languages and scenarios - Mitko Sabev, Bistra Andreeva, Bernd Möbius, Ivan Yuen, Omnia Ibrahim:
The effects of lexical frequency on anticipatory voice assimilation in Bulgarian obstruents - Markus Huber-Liebl, Tillmann Rosenow, Ronald Römer, Günther Wirsching, Matthias Wolff:
It all starts with a little difference tensors as data and code - Ian S. Howard:
State space model of airflow in the human vocal apparatus
Posters
- P1 Harald Höge:
Cortical segmentation of syllables based on phases of Θ-cycles - P2 Daniel Schuhmann, Philipp L. Harnisch, Stefan Hillmann:
Relationship between speaking speed and pleasantness of listening speed - P3 Marcella Palladino:
Politolinguistics through spoken language processing: A methodological framework for German and Italian political speeches. - P4 Shushen Manakhimova, Vivien Macketanz, Sebastian Möller:
Quality of experience of German machine translation and automatic text summarization - P5 Maria K. Wolters, Tatjana Kukic, Stefan Hillmann:
Adapting a student-facing chatbot to the needs of first generation students: a user experience study - P6 Lisa Winkler, Melanie Schindler, Aaricia Herygers, Christian Gaida, Felix Gräßer, Rico Petrick, Frank Eisenhaber, Matthias Henker:
Modular text normalization pipeline for language model training - P7 Diana Marie Schenke, Timo Baumann:
Length-controlled natural language generation - P8 Jan Marquenie, Mareile Leonhardt, Sven Grawunder, Ingo Siegert:
Gender spectrum data from podcasts -- a proof of concept - P9 Valentin Kany, Jürgen Trouvain:
Annotation of disfluencies in child speech - P10 Ibrahim Siddig, Sviatoslav Tugeev, Munir Georges:
Pattern-based parsing of German traffic regulations (STVO) for legal knowledge graph construction - P11 Neha Deshpande, Stefan Hillmann, Sebastian Möller:
Evaluating chain-of-thought prompting for abstractive dialogue summarization with large language models for German - P12 Neda Mousavi, Sven Grawunder:
An unsupervised approach to exploring speaking task complexity based on fluency metrics - P13 Robin Bitterlich, Oliver Jokisch, Ullrich Prax, Rocco Zimmermann:
Experimente zur Transkription von Verwaltungsbesprechungen und domänenangepasste Ergebnisprotokollierung - P14 Martha Schubert, Matthias Busch, Julia Krüger, Ingo Siegert:
Speech technology in psychotherapy: exploring transcription tools and their potential impact - P15 Anderson de Lima Luiz, Shubham Vijay Kurlekar, Munir Georges:
Scalable engine and the performance of different LLM models in a slurm based HPC architecture
Show & Tell
- S1 Arne-Lukas Fietkau, João Menezes, Jihyeon Yun, Peter Birkholz:
Optopalatographic device “OPG2023” - S2 Lia Frischholz, Lisa Winkler, Christian Gaida, Felix Gräßer:
STRUKTUR 2.0 – From free speech input to structured reporting in radiology - S3 Judith Pietschmann, Susanne Voigt-Zimmermann, Elisabeth Zeuner, Richard Fiebelkorn, Eugenia Rykova, Mathias Walther:
Avatar-gestützte digitale Aphasietherapie im Projekt APHADIGITAL – Prototyp der therapeutischen Komponenten - S4 Dalida Valeeva:
Voice and personality – music psychological aspects in speech perception - S5 Konstantin Sering, Yu-Hsiang Tseng, Adriana Hanulíková:
Phonetic distances in L3-speech