Program

Workshop Program

Wednesday, October 28, 2026 · Room F9-10 · Budapest, Hungary
All times are local Budapest time (CET, UTC+1).
TimeSession
Session 1 (9:00 – 11:00)
9:00 – 9:05Opening Ceremony
9:05 – 10:00Keynote 1: Philipp Koehn (Johns Hopkins University)
10:00 – 11:00Keynote 2: Berrak Sisman (Johns Hopkins University)
11:00 – 11:30Coffee Break
Session 2 (11:30 – 12:30)
11:30 – 12:30Keynote 3: Gabriel Skantze (KTH Royal Institute of Technology)
12:30 – 14:00Lunch Break & Poster Session · Boards 297–309 (see the list of posters below)
Session 3 (14:00 – 15:00)
14:00 – 15:00Keynote 4: Sebastian Möller (Technische Universität Berlin)
15:00 – 15:30Coffee Break
Session 4 (15:30 – 17:35)
15:30 – 16:30Keynote 5: Piotr Żelasko (NVIDIA)
16:30 – 17:30Keynote 6: Julia Hirschberg (Columbia University)
17:30 – 17:35Closing Ceremony & Best Paper Awards

Poster Session

All accepted papers are presented as posters during the lunch break, 12:30 – 14:00, on boards 297–309. Presenters: please use these boards to display your posters.

  1. CVSS-X: A Multilingual Speech-to-Speech Translation Corpus for 28 Languages
    Lucas Rafael Stefanel Gris, Alef Iury Siqueira Ferreira, F S de Oliveira, Augusto Seben da Rosa, Alexandre Costa Ferro Filho, Arlindo Rodrigues Galvão Filho and Anderson Da Silva Soares
    Presenter: Alef Iury Siqueira Ferreira (virtual)
  2. TurnStyle: Suggesting Style Prompts for Instruction-Guided Text-to-Speech Using Bimodal Dialogue Contexts
    Jack McLaughlin and Cecilia O Alm
    Presenter: Jack McLaughlin (virtual)
  3. KanAdapter: A Kolmogorov-Arnold Network-based Plug-and-Play Module for Efficient Fine-tuning of Foundation Speech Models
    Phuong Tuan Dat
    Presenter: Phuong Tuan Dat (virtual)
  4. Disentangled Global-Local Feature Learning with E-Branchformer for Audio Deepfake Detection
    Phuong Tuan Dat, Ho Bao Thu, Trung Nguyen Tran, Viet Hoang Pham and Nguyen Thi Thu Trang
    Presenter: Phuong Tuan Dat (virtual)
  5. Nuha-Speech: Building General-Purpose Arabic Speech-LLMs
    Yingzhi Wang, Reem Alhazzani and Muhammad AL-Qurishi
    Presenter: Yingzhi Wang
  6. When How You Speak Changes What Models Refuse: Investigating Prosody-Conditioned Safety Divergence in Audio-Language Models
    Akash Das and Ishan Roy
    Presenter: Akash Das (virtual)
  7. Gold-Preserving Synthetic Augmentation for Verbatim Swedish Automatic Speech Recognition
    Giuseppe Chiriatti, Dimitrios Kokkinakis, Flavio Bertini, Ricardo Muñoz Sánchez and Herbert Lange
    Presenter: Giuseppe Chiriatti
  8. Pragmatic Semantic Communication of Scene Description for Blind and Low-Vision Users
    Peng Wu, Ruxiao Chen and Shuaishuai Guo
    Presenter: Shuaishuai Guo
  9. Lost in Speech: Trilingual Spoken Hallucination Detection Across Audio and Transcripts
    Meruyert Aristombayeva, Jason S Lucas, Chaewan Chun and Dongwon Lee
    Presenter: Chaewan Chun
  10. Improving Urdu ASR with Fine-Tuned Small Language Models for Post-ASR Error Correction
    Sajjad Haider, Solat J. Sheikh, Zuha Aqib, Farah Inayat and Zehra Ahmed
    Presenter: Sajjad Haider
  11. SEABED: SouthEast Asian Benchmark for Evaluating Audio Reasoning
    Harshit Rajgarhia, Asif Shaik, Rachuri Lokesh, Sushanta Kumar Pani and Abhishek Mukherji
    Presenter: Aryan Vijay Bhosale
  12. TORUS: A Test of Rendering-Understanding Self-Coherence for Unified Audio Models
    Aryan Vijay Bhosale, Harshit Rajgarhia, Abhishek Mukherji and Dinesh Manocha
    Presenter: Aryan Vijay Bhosale
  13. Am I Audible Now? Dissecting Prosody in Neural Audio Codecs
    Nikunj Gupta, Shreshth Rai, Kartik Sharma and Dinesh K Vishwakarma
    Presenter: Shreshth Rai (virtual)
  14. Focus, LLMs! Evaluating Focus Sensitivity in Text and Audio Language Models
    Marie-Léontine Wörgötter, Gaurav Kamath and Sebastian Schuster
    Presenter: Marie-Léontine Wörgötter
  15. Echoes in Plato's Cave: Measuring Global and Local Alignment Between Speech and Language Representations
    Alef Iury Siqueira Ferreira, Lucas Rafael Stefanel Gris, F S de Oliveira, Arlindo Rodrigues Galvão Filho and Anderson Da Silva Soares
    Presenter: Alef Iury Siqueira Ferreira (virtual)
  16. CoSE-E: A Benchmark for Code-switched Speech Evaluation in Enterprise Settings
    Shama Gupta, Hoang H Nguyen, Chelsea Huang, Lindsay Devon Brin and Fanny Riols
    Presenter: Shama Gupta (virtual)
  17. Context-Aware Multimodal Claim Verification in Spoken Dialogues
    Chaewan Chun, Delvin Ce Zhang and Dongwon Lee
    Presenter: Chaewan Chun
  18. Lipi-Ghor: A Large-Scale, Diarized, Multi-Domain Bengali Speech Corpus and a Scalable Pipeline for Building It
    Sanjid Hasan, Ahm Fuad, Risalat Labib and Bayazid Hasan Simon
    Presenter: Sanjid Hasan (virtual)
  19. MENASpeechBank: A Reference Voice Bank with Persona-Conditioned Multi-Turn Conversations for SpeechLLMs
    Zien Sheikh Ali, Hunzalah Hassan Bhatti, Rabindra Nath Nandi, Shammur Absar Chowdhury and Firoj Alam
    Presenter: Firoj Alam