This is a preliminary conference program - please check the scheduled time of your talk.

For technical details see the equipment list.

Overview
Date	Time	Action	Room
Tuesday, September 1, 2026	10:00 - 16:00	Reserved for possible satellite workshop	Hall 4
	16:00 - 18:00	Registration	Lounge
Wednesday, September 2, 2026	8:00 - 9:00	Registration	Lounge
	9:00 - 9:20	Opening Session	Hall 5
	9:20 - 10:20	Anders Søgaard : Zombie Interlocutors: How Hard Is Natural Language Processing? - invited talk	Hall 5
	10:20 - 10:35	Coffee Break	Lounge
	10:35 - 12:15	Parallel Sessions (2 x 4)	Hall 5, Hall 4
	12:15 - 13:30	Lunch Break	Restaurant
	13:30 - 14:30	Poster Session 1	Lounge
	14:30 - 16:10	Parallel Sessions (2 x 4)	Hall 5, Hall 4
	16:10 - 16:25	Coffee Break	Lounge
	16:25 - 17:30	Demo Session and Poster Session 2	Hall 4 and Lounge
	16:30 - 17:30	Program Committee Meeting	Hall 5
	18:00 - 20:00	Welcome Reception	Restaurant
Thursday, September 3, 2026	09:00 - 10:15	Parallel Sessions (2 x 3)	Hall 5, Hall 4
	10:15 - 10:30	Coffee Break	Lounge
	10:30 - 11:45	Parallel Sessions (2 x 3)	Hall 5, Hall 4
	11:45 - 12:45	Lunch Break	Restaurant
	12:45 - 23:00	Trip and Conference Dinner
Friday, September 4, 2026	9:30 - 10:30	Giuseppe Riccardi: AI: The Good, the Bad, and the Ugly - invited talk	Hall 5
	10:30 - 10:45	Coffee Break	Lounge
	10:45 - 12:25	Parallel Sessions (2 x 4)	Hall 5, Hall 4
	12:25 - 12:30	Closing Ceremony	Hall 5
	12:30 - 13:30	Lunch Break	Restaurant

Wednesday, September 2, 2026
Time
8:00	Registration (Lounge)
9:00	Opening Session (Hall 5)
9:20	Anders Søgaard : Zombie Interlocutors: How Hard Is Natural Language Processing? - invited talk (Hall 5)
10:20	Coffee Break (Lounge)
	Parallel Sessions (2 x 4)
	Section Text (Hall 5)	Section Speech (Hall 4)
10:35	#1370: Vojtěch John and Zdeněk Žabokrtský: LLMs as Linguistic Experts: The Case of Morphological Segmentation (oral)	#1328: Johannes Wirth: OLaPh: Optimal Language Phonemizer (oral)
11:00	#1356: Duje Jurić and Teo Matošević and Teo Radolović and Marina Bagić Babac}: Evaluation of Transformer Language Models for Hate Speech Detection in Croatian Online Text (oral)	#1353: Daniel Tihelka and Zdeněk Hanzlíček: On the Influence of VITS Initialisation on Speech Quality (oral)
11:25	#1321: Adam Frémund and Jan Švec: Context as a Key: Quantifying Verbatim Data Leakage Across Model Scale, Alignment, and Reasoning Architectures (oral)	#1344: Juan Camilo Vásquez-Correa and Haritz Arzelus and Aitor Álvarez: Syllable Stress Detection to Evaluate Pathological Speech and L2 Language Level Pronunciation (oral)
11:50	#1359: Lars Bungum and Oscar Andreas Halvorsen and Jon Atle Gulla: Large Language Models for Norwegian Bokmål-Nynorsk Translation: Scaling Laws and the Limits of Back-Translation (oral)	#1387: Jhon Fredy Mercado-Agudelo and Daniel Escobar-Grisales and Cristian David Ríos-Urrego and Jeferson David Gallo-Aristizábal and Juan Rafael Orozco-Arroyave: Cross-Attention Fusion of Acoustic and Linguistic Features for Parkinson's Disease Detection (oral)
12:15	Lunch Break (Restaurant)
13:30	Poster Session 1 (Lounge)
	#1311: Gokul Srinivasagan and Munir Georges: Location-Aware Language Models via Secondary Embeddings (poster)	#1324: Konstantinos Diamantopoulos and Stergios Chatzikyriakidis: Gender Bias in Greek Pronoun Resolution: Evaluating Multilingual and Language-Specific LLMs (poster)
	#1333: Alexander Chulzhanov and Soeren Eberhardt and Arjun Mukherjee: Data Synthesis and Parameter-Efficient Fine-Tuning for Low-Resource NMT: A Case Study on Q'eqchi' Mayan (poster)	#1355: Danuta Roszko and Roman Roszko and Piotr Szatkowski: Building Data Infrastructure and LLM Benchmarks for the Masurian Dialect (poster)
	#1323: Nguyen Thanh Binh and Le Phuoc Cuong and Nguyen Quoc Hieu and Hoang Quoc Hung and Do Minh Quang and Nguyen Khanh Linh and Nguyen Quang Tuan: Cross-lingual Text-to-speech Translation for Regional, Low-resource Languages in Vietnam (poster)	#1326: Yun-Ting Sun and Kai-Chen Tsai and Tien-Hong Lo and Jeih-Weih Hung and Berlin Chen: Contextual Biasing for Streaming Automatic Speech Recognition via Phoneme-Fused Representation and Detect-Then-Inject Decoding (poster)
	#1335: Máté Gedeon and Péter Mihajlik: LibriConvo: Simulating Conversations from Read Literature for ASR and Diarization (poster)	#1361: Tomáš Černáček and Milan Rusko: Early Alzheimer’s Detection Using Siamese Conformer Networks on Slovak Confrontation Naming Tasks (poster)
	#1327: Filip Polák and Jan Tupý and Luboš Šmídl and Aleš Bartoš: From Paper to Speech: ASR-Driven Digitalization of the PICNIR Cognitive Test (poster)	#1334: Lukas Torquato and Rejwanul Haque and Paul Stynes and Greg Doyle and Oisin Cawley: Blackwell: An Explainable Anamnesis-based Multi-Agent Framework for Remote Clinical Diagnosis (poster)
	Parallel Sessions (2 x 4)
	Section Text (Hall 5)	Section Dialogue (Hall 4)
14:30	#1371: Edoardo Signoroni and Pavel Rychlý: ``Chi nas dal soch el sent de legn'' (oral)	#1342: Jana Winkler and Barbara Schuppler: Turn-by-Turn Acoustic-Prosodic Alignment and its Relationship to Lexical and Semantic Similarity in Casual Conversations (oral)
14:55	#1312: Ane Varela and Arantza Casillas and Maite Oronoz: Using Explainable AI to Identify Spanish SDOH Keywords (oral)	#1365: Ting-An Hung and Yu-Hsuan Hsieh and Tien-Hong Lo and Hong-Yun Lin and Yung-Chang Hsu and Berlin Chen: An Effective Structured Generation Approach to Sentence Stress Detection with Speech Language Models (oral)
15:20	#1351: Péter Kardos and Máté Vass and Miklós Krész and Richárd Farkas: Large Language Models for Sparse Entity Alignment over Knowledge Graphs (oral)	#1317: Michael Paierl and Barbara Schuppler: Communicative Function Classification using Voice Activity Projection (oral)
15:45	#1396: Martin Dvořák and Vít Tlustoš and Artyom Voronin and Martin Habrovec and Kateřina Podlesná and Barbora Rišová and Josef Vonášek: Size Matters: Foundation Model for Czech HTML Documents (oral)	#1337: Valentin Vielzeuf and Antoine Caubrière: Utterance-Level Spoken Embeddings for Dialogue State Tracking (oral)
16:10	Coffee Break (Lounge)
16:25	Demo Session and Poster Session 2 (Hall 4 and Lounge)
	#_1270 (demo)	#_1300 (demo)
	#_1301 (demo)	#_1280 (demo)
	#1362: Sajjad Hadi and Christopher Hauer and Philipp Klumpp and Elmar Nöth and Andreas Maier and Tomás Arias-Vergara: Tremor Vision: Cross-Domain Multiclass Plosive Burst Detection from Audio-Derived Spectrogram Images for Parkinsonian DDK Speech Analysis (poster)	#1386: J.D. Gallo-Aristizábal and C.D. Ríos-Urrego and D. Escobar-Grisales and J.F Mercado-Agudelo and J. R. Orozco-Arroyave: On the Explainability of Speech Impairment Regarding Dysarthria Progression in Parkinson's Disease (poster)
	#1394: Christopher Simic and Korbinian Riedhammer and Sebastian Bayerl and Tobias Bocklet: Benchmarking Pretrained Speech Models for Arabic Dialect Identification with Cross-Corpus Evaluation (poster)	#1404: Ben Jurkovič and Radim Krupička and Ondřej Klempíř: Cross-Database Performance of Speech-Based Graph Neural Networks for Parkinson’s Disease Detection (poster)
	#1336: Jan Šimek and Marie Kunešová and Jindřich Matoušek: Comparing Acoustic and Linguistic Features for Automated Deception Detection (poster)	#1410: Nicholas Gareth Jennings and Volha Petukhova and Dietrich Klakow: OnkoRAG: Modelling Cross-Lingual German-Arabic Medical Question Answering (poster)
	#1367: Lauma Pretkalniņa and Krasimir Angelov and Kristīne Pokratniece and Normunds Grūzītis: Large-Scale Computational Morphology and Lexical Resources for Latvian and Latgalian (poster)	#1381: Martin Chotár and Matúš Kleštinec and Daša Munková: Evaluating the Effect of Fine-Tuning on Usability Annotation of English-Slovak Translation (poster)
	#1391: Rinalds Vīksna and Mārcis Pinnis: Pseudonymisation for Morphologically Rich Languages (poster)
17:30
16:30	Program Committee Meeting (Hall 5)
17:30
18:00	Welcome Reception (Restaurant)
20:00

Thursday, September 3, 2026
Time	Parallel Sessions (2 x 3)
	Section Text/Speech (Hall 5)	Section Dialogue (Hall 4)
09:00	#1316: Tomáš Jelínek and Hana Skoumalová: SYN_r25: a Corpus Linked to a Database of Multi-Word Expressions (oral)	#1319: Sophie Lennkh and Michael Paierl and Barbara Schuppler: GRASS - HRI: A Corpus of Spontaneous Austrian German Dialogues with the Social Robot Furhat (oral)
09:25	#1403: Igor Lourenço Bartijotto Manzano Bento and Stephany Xesquevixos and Yingqiang Gao and Patricia Puppin Mandrá and Alessandra Alaniz Macedo: SofiaFala ECOA: A Framework for Multimodal Corpora Construction for Speech Disorder Analysis and Assistive AI Systems (oral)	#1345: Juan Camilo Vásquez-Correa and Eneko Tomé and Haritz Arzelus and Ana Díaz de Zugazúa and Sara Sillaurren and Aitor Álvarez: Multimodal Speech Recognition in High-Noise Factory Floors for Human Robot Collaboration (oral)
09:50	#1322: Lukas Graf and Christian Bergler: SYNODA: Synthetic Data-Oriented Domain Adaptation for Automatic Speech Recognition (oral)	#1364: Franziska Braun and Alea Rüggeberg and Thomas Ranzenberger and Hartmut Lehfeld and Thomas Hillemacher and Tobias Bocklet and Korbinian Riedhammer: Reading between the Lines: Leveraging Large Language Models for Global Dementia and Depression Assessment from Clinical Interviews (oral)
10:15	Coffee Break (Lounge)
	Parallel Sessions (2 x 3)
	Section Dialogue (Hall 5)	Section Speech (Hall 4)
10:30	#1357: Esaú Villatoro-Tello and Ernesto A. Reyes-Ramírez and Sergio Burdisso and Hasindri Watawana and Petr Motlíček and Fernando Sánchez-Vega and A. Pastor López-Monroy: Modelling Thematic Structure in Clinical Dialogues for Interpretable Depression Detection (oral)	#1350: Jindřich Matoušek and Luboš Šmídl and Paula Andrea Pérez-Toro and Elmar Nöth and Jan Lehečka and Andreas Maier and Tomás Arias-Vergara: On the Synthesis of Dysarthric Speech: Evaluating Zero-Shot and Fine-Tuning Approaches (oral)
10:55	#1354: David Escudero-Mancebo and Melquiades Rodríguez and Guillermo Vicente-Oliva: Analysis and Implications of Alignment Between LLM-as-a-Judge and Human Evaluators in a Generative AI Chatbot: A Real-World Study (oral)	#1358: Philippe Martin and David Guennec and Vincent Barreaud and Nelly Barbot and Damien Lolive: On the Robustness to Recording Condition of Speaker and Accent Embeddings for a Voice Cloning System (oral)
11:20	#1360: Matyáš Veselý and Michal Průšek and Jiří Franc: Your Retriever Already Knows: Predicting RAG Retrieval Sufficiency from Score Distributions (oral)
11:45	Lunch Break (Restaurant)
12:45	Trip and Conference Dinner
23:00

Friday, September 4, 2026
Time
9:30	Giuseppe Riccardi: AI: The Good, the Bad, and the Ugly - invited talk (Hall 5)
10:30	Coffee Break (Lounge)
	Parallel Sessions (2 x 4)
	Section Text (Hall 5)	Section Speech (Hall 4)
10:45	#1412: Martin Poláček and Petr Červa and Lukáš Matějů: Online Punctuation and Capitalization Restoration Using Seq2Seq Approach (oral)	#1379: Zdeněk Hanzlíček and Jindřich Matoušek and Daniel Tihelka and Jan Lehečka: Leveraging Zero-Shot TTS for Data Augmentation: A Comparison of VITS and StyleTTS2 in Low-Resource and Low-Quality Conditions (oral)
11:10	#1383: Yevhenii Karpizenkov and Ales Horak and Radim Lacina: Benchmarking Pragmatic Reasoning of Large Language Models in the Czech Language (oral)	#1348: Tomáš Lebeda and Jan Švec and Luboš Šmídl: Evaluating the Sufficiency of Verbal Picture Description Task for Cognitive Impairment Detection (oral)
11:35	#1320: Kennedy Roland and Milton King: Is this Funny to You?: A Reader-Aware Humour Classification Dataset (oral)	#1352: Jan Lehečka and Josef V. Psutka and Aleš Pražák and Josef Psutka: Optimizing Streaming Zipformer for Czech Humanoid Robotics: Balancing Accuracy, Latency, and Ego-Noise (oral)
12:00	#1392: Botir Elov and Gulbahor Iskandarova and Xusniddin Xaitov and Dilrabo Khikmatova and Shahnoza O'dayeva and Sayyora Abdurahmanova and Aynura Akhmedova: UzbekSpell: An Annotated Benchmark Corpus for Error Detection and Correction in Uzbek (oral)	#1409: Martin Motejlek and Jiří Málek and Petr Červa: Acoustic Volume Mismatch in Distant Streaming ASR: Case Study and Mitigation via Wide-Range Volume Perturbation (oral)
12:25	Closing Ceremony (Hall 5)
12:30	Lunch Break (Restaurant)
13:30