Organizers

Aref Farhadipour is a PhD student in the Department of Computational Linguistics at the University of Zurich, where he works on multimodal speaker recognition using voice, face, and gesture modalities. With a master's degree in sound engineering, his research interests include speaker and face recognition, multimodal learning, and audio-LLMs.

Jan Marquenie is a PhD student in the Group Mobile Dialog Systems at the Otto-von-Guericke University Magdeburg, focusing on speech privacy, speaker verification, and video anonymization. His research centers on the evaluation of de-identification methods and their impact on data utility. With a background in human–machine interaction, his work bridges speech security and multimodal interaction.

Srikanth Madikeri is an academic associate in the Department of Computational Linguistics at the University of Zürich. He holds a PhD in Computer Science and Engineering from the Indian Institute of Technology Madras, where he specialized in speaker recognition and spoken keyword spotting. Before joining UZH, he worked at the Idiap Research Institute as a research associate. His research focuses on speech and language technologies, including low-resource automatic speech recognition, speaker and language recognition, and spoken dialogue systems.

Volker Dellwo is Associate Professor of Phonetics at the University of Zurich, specializing in speech and voice sciences. His work focuses on how indexical information is encoded in and extracted from speech, and how this interacts with linguistic content. He is engaged in forensic phonetics, speaker recognition, speech rhythm, and variation across dialects, time, and social contexts.

Teodora Vukovic is a postdoctoral researcher in the Digital Society Initiative at the University of Zurich. Her work centers on CAPIRE, a project investigating how people are identified from multimodal behavioral signals such as vocal acoustics, speech, facial expressions, and gestures in real interaction settings. She also researches data anonymization techniques to preserve privacy.

Kathy Reid is a PhD student at the Australian National University's School of Cybernetics, where her research explores voice data and dataset documentation to promote more inclusive and equitable speech technologies. She holds a Research Partnership with the Mozilla Foundation, collaborating with the Common Voice team. Her expertise spans data visualization, research methods, data engineering, and speech recognition.

Francis M. Tyers is Associate Professor of Linguistics at Indiana University, specializing in computational linguistics with a focus on marginalized languages. His research centers on the development of linguistic resources and methods for analyzing morphosyntax, as well as the design of systems for machine translation and dependency parsing. He is an active contributor to open-source language technology projects and works to advance the accessibility of digital tools for under-represented languages.

Ingo Siegert is a Privatdozent in Speech and Language Technology at Otto von Guericke University Magdeburg and Head of the research group AI-Based Assistance Systems in Psychosomatic and Psychotherapeutic Contexts at the University Hospital Magdeburg. He is Chair of the SIG Security and Privacy in Speech Communication and organizes the yearly SPSC Symposium. His work spans from privacy-preserving voice analytics and speech-based human–machine interaction, to affective and pathological speech processing, and ethical AI in voice technologies.

Eleanor Chodroff is an SNF Professor at the University of Zurich in the Department of Computational Linguistics. Her research focuses on phonetic variation across speakers and languages. She regularly uses computational techniques and large-scale data processing to understand cognitive and AI representations of speech and voice. She has previously organized shared tasks and workshops for SIGMORPHON, an ACL Special Interest Group on computational approaches to Morphology, Phonology and Phonetics.