Programm

Dienstag, 05.03.2024

ITG-Workshop Sprachassistenten, Dinner auf Selbstzahlerbasis im Café Charlotte (reserviert ist ab 19:00)

Wissenschaftliche Beiträge

Hauptvorträge

• Anna Kruspe: More Than Words: Advancements and Challenges in Speech Recognition for Singing
• Hendrik Buschmeier: Linguistic Politeness in Artificial Conversational Agents

Chatbots und Dialogsysteme

Sitzungsleiter: Ingo Siegert

• Stefan Schaffer, Eva Schwaetzer, Aaron Ruß, Oliver Gustke: Chatbot in the Museum – A Field Study of User Experience and Modality Usage
• Stefan Hillmann, Philine Kowol, Adnan Ahmad, Ruochen Tang, Sebastian Möller: Usability and User Experience of a Chatbot for Student Support
• Mathias Walther, Elisabeth Zeuner, Eugenia Rykova: Interaktionsverhalten eines Avatars im digitalen sprachtherapeutischen Setting
• Lea Kisser, Matthias Busch, Ingo Siegert: Review of Usage and potentials of Conversational Interfaces at Universities and in Students' Daily Lives

Phonetische Untersuchungen

Sitzungsleiter: Ronald Böck

• Uliana Eliseeva, Ivan Yuen, Bernd Möbius: Perception of Formant Distortion in German Words and Non-words
• João Vítor Possamai de Menezes, Christian Kleiner, Marie-Anne Kainz, Matthias Echternach, Peter Birkholz: Synchrony of Glottal Area Waveform Parameters During the Production of Obstruents in Vowel Context
• Valentin Kany, Jürgen Trouvain: Computergestützte Bestimmung des Sprechflusses bei Vorschulkindern
• Harald Höge: The Use of Temporal Features in Cortical Segmentation of Syllable

Spracherkennung und -verstehen

Sitzungsleiter: Sebastian Möller

• Johannes Kuhn, Matthias Wolff, Borislav Borislavov: Epsilon-Verarbeitung bei Minimalistischen Grammatiken für Zahlen
• Mariano Frohnmaier, Steffen Freisinger, Madeline Faye Holt, Munir Georges: NoiSLU: A Noisy Speech Corpus for Spoken Language Understanding in the Public Transport Domain
• Markus Huber-Liebl, Günther Wirsching: Ein quantenlogisch motivierter Ansatz zur Verarbeitung von Äußerungs-Bedeutungspaaren
• Christoph Draxler, Julian Pömp: Octra Backend – Eine skalierbare Infrastruktur für Transkriptionsprojekte

Paralinguistische Analysen

Sitzungsleiter: Bernd Möbius

• Peter Birkholz, Xinyu Zhang: An Investigation of Acoustic Features of the Lower Vocal Tract for Speaker Recognition
• Anjana Rajasekhar, Anna Leschanowsky, Nils Peters: Towards Speech Privacy Assessment for Voice Assistants: Exploring Subjective and Objective Measures for Babble Noise
• Thorben Frank Jahnke, Corinna Sonnen, Mathias Walther: Konzept und Evaluation eines Softwaresystems zur Unterstützung der CRM-basierten Sprechwirkungsuntersuchung → als Poster
• Tobias Blaabjerg Karlsen, Karl Jhon Decuzar de Castro, Emils Pipars, Iyad Ahed Abdelrahman Abdel Qader, Jose Dumitru Ilinca Sainz, Simas Srugys, Oliver Niebuhr: In Tune With In-Poco? A New Device for Analyzing and Training the Interplay of Body Posture and Charismatic Speech Prosody

Large Language Models

Sitzungsleiter: Peter Birkholz

• Siddarth Venkateswaran, Ronald Böck: Can Language Models Behave Like Wine Sommeliers? Using Multiple Agents To Evaluate The Quality of Wine Descriptors Generated By Llama 2
• Benedict Kettler, Stefan Hillmann: Supervised vs. Zero-Shot Learning Automatic Classification of Comments on Educational Videos Using Pre-Trained Language Models
• Siddarth Venkateswaran, Abdullah Al Foysal, Nazeer Basha Shaik, Ronald Böck: Is there Text in Wine? – S+U Learning-Based Named Entity Recognition and Triplet Extraction from Wine Aroma Descriptors
• Christian Schuler, Debjoy Saha, Shravan Nayak, Timo Baumann: Can We See Your Response Before You Speak? Exploring Linguistic Information Found in Inter-Turn Pauses

Sprachsynthese und Hörpräferenzen

Sitzungsleiter: Jürgen Trouvain

• Konstantin Sering: Speech/Non-Speech Classification Slightly Improves Synthesis Quality in PAULE
• Yamini Sinha, Jan Hintz, Ingo Siegert: Evaluation of Audio Deepfakes – Systematic Review
• Judith Bauer, Frank Zalkow, Meinard Müller, Christian Dittmar: Evaluating the Impact of Prosody Feature Normalization on the Controllability of Pitch in Speech Synthesis
• Omnia Ibrahim, Ivan Yuen, Wei Xue, Bistra Andreeva, Bernd Möbius: Listener-Oriented Consequences of Predictability-Based Acoustic Adjustment

Poster

• Martha Schubert, Yamini Sinha, Julia Krüger, Ingo Siegert: Speech Recognition Errors in ASR Engines and Their Impact on Linguistic Analysis in Psychotherapies
• Philipp L. Harnisch, Stefan Hillmann: Empirical Evaluation of ASR and NLU in a Multimodal Dialogue System for Survey Answering
• Thomas Ranzenberger, Tobias Bocklet, Steffen Freisinger, Munir Georges, Kevin Glocker, Aaricia Herygers, Korbinian Riedhammer, Fabian Schneider, Christopher Simic, Khabbab Zakaria: Extending HAnS: Large Language Models for Question Answering, Summarization, and Topic Segmentation in an ML-based Learning Experience Platform
• Neda Mousavi, Sven Grawunder: The Influence of Signal Segmentation Methods on Rhythm-Based Speaker Recognition
• Neda Mousavi, Seyyed Saeed Sarfjoo, Sven Grawunder: Unsupervised Emotional Pattern Recognition Using Rhythmic and Vocal Features
• Ïo Valls-Ratés, Oliver Niebuhr: VirtuVoce: The World's (Very) First Voice Gym

Wir bedanken uns herzlich bei unseren Sponsoren: