First day (September 25, 2026)

Opening Session

09:15–09:30

Session 1  Speech Representations and Robust Recognition

09:30–11:10  |  5 presentations

09:30–09:50  |  Paper 84

Probing the phon* representations of the Mimi codebooks

Artem Saloev; Nicolas Ballier; Erin Pacquetet

09:50–10:10  |  Paper 95

Listening for Speaker Identity in Multilingual Speech Models: Phonetic Similarity Predicts Transfer in Cross-Lingual Speaker Verification

AriaRay Brown; Yusser Al Ghussin; Dietrich Klakow

10:10–10:30  |  Paper 47

Revisiting Accent Classification with DistilHuBERT: Speaker-Disjoint Evaluation and Cross-Corpus Generalization

Xu He; Homayoon Beigi

10:30–10:50  |  Paper 87

Adaptive Multi-Teacher Distillation for Accent-Robust Speech Recognition

Mehedi Bijoy; Dejan Porjazovski; Tamás Grósz; Mikko Kurimo

10:50–11:10  |  Paper 48

Token Merging for Multilingual Speech Recognition: A Systematic Study Across Model Scale and Fine-Tuning

Dylan Holyoak

Session 2  Speech Recognition for Specialized Domains and Underrepresented Speakers

11:25–13:05  |  5 presentations

11:25–11:45  |  Paper 85

Seeds Before Objectives: Rethinking Evaluation for Low-Resource Garhwali ASR

Karamvir Singh Batra; Prathamjyot Singh; Ashima Sood; Jasmeet Singh; Sahil Sharma

11:45–12:05  |  Paper 58

Budgeting Speech-to-LLM ASR for Underrepresented Dutch Speech

Xinnian Zhao; Hugo Vanhamme; Pu Wang

12:05–12:25  |  Paper 40

Does Financial Speech Need Continual Learning Regularization? A Study of EWC and mini-KFAC on Earnings Call ASR

Thai On; Homayoon Beigi

12:25–12:45  |  Paper 23

myMediWhisper: Construction of Burmese Medical Speech Corpus and Whisper Fine-Tuning for Clinical Dialogue ASR

Ye Kyaw Thu; Ye Bhone Lin; Thura Aung; Htet Arkar; Myat Oo Swe; Thet Htet San; Min Thiha Tun; Thazin Myint Oo; Thepchai Supnithi

12:45–13:05  |  Paper 86

Towards a clinical adaptation of the Whisper model for French

Haeeul Hwang; Deok-Hee Kim-Dufor; Jalal Al-Tamimi; Motasem Alrahabi; Julien Desclés; Valeria Lucarini; Louis Pichereau; Christophe Lemey

Session 3  Linguistic Analysis and Multilingual Language Resources

14:05–15:25  |  4 presentations

14:05–14:25  |  Paper 70

Combined Learning of Morphological Segmentation, POS Tagging and Contextual Lemmatization

Christian Wartena

14:25–14:45  |  Paper 93

Evaluating Latent Semantic Pre-training for Fine-grained Word Sense Disambiguation

Soma Simon; Gábor Berend

14:45–15:05  |  Paper 76

A Multimodal Corpus for Natural Language Understanding in Russian and Tatar

Alsu Khabirzyanova; Zaryana Damashova; Ilseyar Alimova

15:05–15:25  |  Paper 71

Evaluating Transformers with NepSum: A Large-Scale Dataset for Nepali Abstractive Summarization

Saskar Khadka; Pawan Khatri

Session 4  Low Resource Translation and Figurative Language

15:40–17:20  |  5 presentations

15:40–16:00  |  Paper 74

When Silver Isn’t Enough: Data Quality Effects on Pnar-English Machine Translation

Riya Tekcham; Fitha Asma Sulfeekhar; Badal Nyalang

16:00–16:20  |  Paper 96

From Folklore to Fine-Tuning: An Authentic Angika-Hindi Parallel Corpus and Warm-Initialized Translation Baseline

Jyoti Kumari

16:20–16:40  |  Paper 94

Looking under the Wrong Lamppost: On the Limitations of Automated Translation Quality Estimation

Serge Gladkoff; Angelika Vaasa; Sue Ellen Wright; Ingemar Strandvik; Lifeng Han

16:40–17:00  |  Paper 89

MetaHOPE: Metaphor Translation Evaluation Framework Investigating Open-Source LLMs and State-of-the-Art Neural Translation Models

Jiahui Liang; lifeng han

17:00–17:20  |  Paper 78

LLM-as-Annotator at 4B Scale: Strategy-Specific Instruction Tuning for Chinese Metaphor Identification

Yufeng WU

Second day (September 26, 2026)

Session 5  Sentiment Emotion and Harmful Language

09:00–10:40  |  5 presentations

09:00–09:20  |  Paper 49

Improving Persian Sentiment Classification through LLM-Assisted Label Refinement and Small Language Models

Maziyar Amini Alashti; Seyed Abbas Bagheri

09:20–09:40  |  Paper 69

Cross-Lingual Transfer Learning for Multilingual Emotion Classification and Generation

Adrian Maldonado; Oscar Araque

09:40–10:00  |  Paper 91

ArImpliSent: A Large-Scale Dataset for Arabic Implicit Sentiment Analysis

Ghozlene Chenni; Sadik Bessou; Hanane Boutouta; Nour elhouda Chenni

10:00–10:20  |  Paper 88

ResPL: Reasoning-Based Pseudo-Labels for Sarcasm Detection in Low-Resource Arabic Dialects

Ali Almutairi; Shoaib Jameel; Aditya Joshi; Gelareh Mohammadi; Imran Razzak

10:20–10:40  |  Paper 51

RomMa-FT: Static Word Embeddings for Romanized Marathi-English Code-Mixed Hate Speech Detection

Nitin Chavan; Dr. Badal Soni

Session 6  Text Organization and Knowledge Extraction

10:55–12:35  |  5 presentations

10:55–11:15  |  Paper 66

Text Segmentation is Subjective: Empirical Evidence of Human Variability and its Implications for Downstream Tasks

Sophia Conrad; Florian Frenken

11:15–11:35  |  Paper 28

Thread-Preserving Chunking for LLM-Based Action Item Extraction from Enterprise Email under Constrained Context Budget

kiyeop kim; Donghoon Cho

11:35–11:55  |  Paper 39

AutoSpecNER: A Fine-Grained Named Entity Recognition Dataset for Vehicle Specification Extraction

Jordan Lee; Filippos Ventirozos; Abdirahman Abdullahm; Ioanna Nteka; Peter Appleby; Matthew Shardlow

11:55–12:15  |  Paper 42

Making the Implicit Explicit: A Domain Ontology-Based Approach for Comprehensive Attribute-Level Knowledge Extraction in Technical Texts

Vatosoa Razafiniary

12:15–12:35  |  Paper 25

Textonomy: A TnT-LLM-Based Approach for Interpretable Topic Modeling at Scale

Noah Zuchna; Martin Stoll; Jan Blechschmidt

Session 7  Reasoning Reliability and Social Bias

13:35–15:35  |  6 presentations

13:35–13:55  |  Paper 31

CURB: Civic Urban Reasoning Benchmark

Oliver Fox; Ellis Solaiman

13:55–14:15  |  Paper 32

When Does Uncertainty Measure RAG Hallucination Risk?

Rajeel Ansari; Tautik Agrahari

14:15–14:35  |  Paper 35

One Bad Juror: Exploring Adversarial Influence and Deliberation Dynamics in Multi-Agent LLM Panels

Vaishakh Menon

14:35–14:55  |  Paper 53

Persona as Infrastructure: Invisible Structural Control in LLM-Mediated Social Networks

Amir Reza Asadi; Jess Kropczynski; Hazem Said

14:55–15:15  |  Paper 67

FrIdéo: French News Outlet Ideology Scoring via Multi-Source Evidence Fusion and Distancing-Aware Lexical Scoring

Amr Sobhy

15:15–15:35  |  Paper 68

Framing by Wording, Framing by Selection: A Large-Scale Two-Dimensional Audit of French News Headlines, 2022–2025

Amr Sobhy

Session 8  Language Learning and Human Communication

15:50–17:30  |  5 presentations

15:50–16:10  |  Paper 54

KidLit by Numbers: Linguistic Profiles of Original and Translated Russian 0+ Books

Daria Gavrilik; Aleksandra Ostraia

16:10–16:30  |  Paper 46

Verbal and Nonverbal Coherence as an Index for Second Language Proficiency

Katsunori Kotani; Takehiko Yoshimi

16:30–16:50  |  Paper 50

Masked Temporal Alignment for Automated Speech Scoring

Akshay Badola; Ikkyu Choi

16:50–17:10  |  Paper 57

Human-in-the-loop Generation System for Analogical Explanations of Target Concepts

Ryo Takahashi; Asuka Terai

17:10–17:30  |  Paper 63

GEMCo: A Validated, Ethically Releasable Proxy for Inaccessible Counselling Data

Philipp Steigerwald; Eric Rudolph; Mara Stieler; Jennifer Burghardt; Robert Lehmann; Jens Albrecht

Closing Session

17:30–17:45