Accepted Papers
Accepted Papers
Menstrual Cycle Tracking through Voice Features
Anika Spiesberger, Technical University of Munich
The Role of Multimodality in Predictive Turn-taking
Sam O'Connor Russell, Trinity College Dublin
Anonymizing with Empathy: Voice Conversion That Preserves What Matters
Suhita Ghosh, Otto von Guericke University
Using Speech Prosody to guide Text Generation by Large Language Models
David Porteš, Masaryk University
Phonetic Perception and Speech Enhancement for Mandarin Listeners of English in Adverse Listening Conditions
Yunqi C. Zhang, University of Auckland
Quantifying anatomical variation in the vocal tract in typical and atypical speakers using 3D MRI
Emily Kiff, University of York
Towards Automatic Voice Disorders Screening: Robustness and Generalisation of Speech-Based Methods in German-Language
Monica Gonzalez Machorro, audEERING GmbH / Technical University of Munich
Understanding and Exploiting Speech Foundation Models for Dialectal ASR: A Case Study on South Tyrolean
Domenico De Cristofaro, Free University of Bozen-Bolzano
Domain Generalization with Bayesian Learning for Speaker Verification and Anti-Spoofing
Jin Li, The Hong Kong Polytechnic University
Expressive Text-to-Speech System for Children in Low-Resource Settings
shaima alwaisi, Budapest University of Technology and Economics
Assessing Quality Dimensions in Speech Foundation Models for Inclusive Dutch ASR
Dragoș Alexandru Bălan, University of Twente
Speech Data Collection and Disfluency Analysis in Ukrainian: Towards Robust ASR for Low-Resourced Language
Anna Havras, VoiceInteraction/University of Lisbon/INESC-ID
Who’s Next?: The Role of Speech Melody in the Turn-Taking System of Dutch
Ariëlle Reitsema, Leiden University
Sociolinguistic Variation in Mandarin: Native and L2 Perspectives on Neutral Tone and Rhotacization
Xiao Dong, Indiana University Bloomington
Minimizing Human Effort in Adaptive Synthetic Speech Quality Assessment via Active Learning
Natacha Miniconi, Le Mans University
Enhancing Ultrasound Tongue Imaging Based Articulation-to-Speech Synthesis
Ibrahim Ibrahimov, Budapest University of Technology and Economics
Attacks by Human-Like Synthetic Speech on Anti-Spoofing Systems: Challenges, Insights, and Solutions
Aurosweta Mahapatra, Johns Hopkins University
Developing a dynamical model of the coordination between melody and syllabic duration in Brazilian Portuguese
Gustavo Silveira, University of Campinas
Controllability and Disentanglement in Expressive Text-to-Speech Systems
David Lindevelt, Leiden University
Development of End to End Speech Translation Models for Indian Languages
Jamaluddin Jamaluddin, Aligarh Muslim University.
Speech Deepfake Detection and Beyond
Yassine El Kheir, DFKI