Location and schedule

Schedule (tentative):

• 08:30-09:00 welcome coffee

  • 09:00-09:30       opening: welcome, introductions

• 09:30-09:45 lightning poster overviews I 

(!!! During the lightning Poster Overview, participants will have up to one minute to present their poster topic and summarize its core message !!!)

• 09:45-10:45 morning poster session

  • 1. 1. 1. 1. • 1. • Poster 1:  Yue Li "Task-Dependent Speech Markers for Predicting Cognitive Status in Older Adults"

                     • Poster 2:  Panagiota Ploumidi "Explainable Anomaly Detection for Speech Deepfakes by Modelling the Human Speech Manifold"

                     • Poster 3: Katie Blackford "Machine learning approaches to model escalation in vocalisation features during frustration in non-verbal children"

                     • Poster 4: Rebecca Li "Perspectives On Differential Voice Data Collection: Traditional Manual Versus Automated Software Methods"

                     • Poster 5: Emilia Pang "Linking Articulatory and Acoustic Measures of Lexical Stress in Healthy Adults"

                     • Poster 6: Anya Goyal "Zero-Shot Dysarthric Speech Reconstruction via Activation Steering of Pretrained TTS Models"

• 10:45-11:15 coffee break

• 11:15-12:15 doctoral student panel

  • 1. 1. 1. 1. • 1. • Monica Gonzalez Machorro (Technical University of Munich / audEERING GmbH)

                     • Sandra Arcos-Holzinger (JHU, University of Melbourne)

                     • Xi Xuan (University of Eastern Finland)

• 12:15-13:15 lunch break

• 13:15-14:15 mentoring

  • 1. 1. 1. 1. • 1. • Jessica Fernando (DataForce by TransPerfect)

Group 1: Katie Blackford, Rebecca Li, Catarina Xie Freire

Group 2: Yue Li, Anya Goyal, Dorota Meszka

• • 1. 1. 1. 1. • 1. • Jude Dineley (King's College London)

Group 1: Yue Li, Anya Goyal, Dorota Meszka

Group 2: Katie Blackford, Rebecca Li, Catarina Xie Freire

• • 1. 1. 1. 1. • 1. • Priyanka Kommagouni (Meeami Technologies)

Group 1: Panagiota Ploumidi, Arun Muthu Venkatesh, Maria Baranova

Group 2: Emilia Pang, Amelia Sasin, Khushi Gatwar

• • 1. 1. 1. 1. • 1. • Chiori Hori (Mitsubishi Electric Research Laboratories)

Group 1: Emilia Pang, Amelia Sasin, Khushi Gatwar

Group 2: Panagiota Ploumidi, Arun Muthu Venkatesh, Maria Baranova

• 14:15-14:30 coffee break

• 14:30-14:45 lightning poster overviews II 

(!!! During the lightning Poster Overview, participants will have up to one minute to present their poster topic and summarize its core message !!!)

• 14:45-15:45 afternoon poster session

  • 1. 1. 1. 1. • 1. • Poster 7:  Catarina Xie Freire "A Unified Platform for Multi-Modal Data Anonymization in European Portuguese"

                     • Poster 8:  Dorota Meszka "Personalized Dysarthric Speech Recognition with Bilingual Phoneme-Level Contrastive Learning: A Case Study"

                     • Poster 9: Arun Muthu Venkatesh "Deepfake Model Source Tracing"

                     • Poster 10: Amelia Sasin "Mixture-of-Experts for Age-Inclusive ASR: Reducing the Adult-Child Performance Gap in Multilingual Speech Recognition"

                     • Poster 11: Khushi Gatwar "Accent-Aware Oral Reading Fluency Assessment for Indian Children: Towards Equitable Speech-Based Education"

                     • Poster 12: Maria Baranova "Evaluating Code-Switching Behaviour in Neural TTS"

• 15:45-16:45 senior panel 

  • 1. 1. 1. 1. • 1. • Abeer Alwan (UCLA, US)

                     • Beena Ahmed (University of New South Wales)

                     • Chiori Hori (Mitsubishi Electric Research Laboratories)

                     • Odette Scharenborg (TU Delft)

  • 16:45-17:00 closing: best poster, final comments, group photo

Biographies of panelists and mentors

• Abeer Alwan received her Ph.D. in Electrical Engineering and Computer Science from MIT in 1992. Since then, she has been with the ECE department at UCLA where she is now a Distinguished Professor of ECE and directs the Speech Processing and Auditory Perception Laboratory (http://www.seas.ucla.edu/spapl/). She is the recipient of the NSF Research Initiation and Career Awards, NIH FIRST, UCLA-TRW Teaching, Okawa Foundation, and the Engineer’s Council Educator Awards. She is a Fellow of ASA, IEEE, and ISCA. She was a Fellow at the Radcliffe Institute, Harvard University, co-Editor in Chief of Speech Communication, Associate Editor of JASA and IEEE TSALP, and on the Board of Governers for the IEEE Signal Processing Society.

• Dr. Beena Ahmed is an Associate Professor in Signal Processing at the School of Electrical Engineering and Telecommunications, UNSW Sydney, Australia. At UNSW, she is the Co-Director of the Signals, Information, and Machine Intelligence Lab and the Technical Lead, Connected Health at the Tyree Foundation Institute of Health Engineering. She is currently leading research projects on the recognition and assessment of children’s and disordered speech, mispronunciation detection in disordered and accented speech as well as identifying the risk of dementia from speech. She has received $9+ million in funding, both local and internationally, and published over 100 career publications. She is also the founder of Say66, where she is translating her research to provide an automated speech therapy system for children with speech disorders. She has received multiple awards for her work in this area including the 2020 Innovation Award from Speech Pathology Australia, 2021 Women in AI and 2022 Telstra Digital Health Award.

• Chiori Hori is a Senior Principal Research Scientist at Mitsubishi Electric Research Laboratories (MERL). She received her Ph.D. from Tokyo Institute of Technology and previously worked at NICT, CMU, and NTT Communication Science Laboratories. Her research spans speech recognition, translation, dialogue systems, multimodal interaction, and human-robot communication. She founded the U-STAR international consortium and contributed to ITU-T standards for speech-to-speech translation. She has also led the Dialog System Technology Challenge (DSTC) since 2017 and helped establish Audio-Visual Scene-Aware Dialog (AVSD). Recently, her research focuses on robot action planning and human-robot interaction, leveraging multimodal large language models and vision-language-action (VLA) models.

• Jessica Fernando  works in AI data and solutions, with 11+ years of experience across generative AI, NLP, text, speech (ASR/TTS), computer vision, and multimodal data. She is also an experienced Industry linguistic specialist in a variety of areas including pronunciation dictionary and language resource development, localisation, voice coaching, annotation of text corpora, and LLMs. She works within a business development function partnering closely with clients to design tailored data strategies that align with their specific objectives and ensure optimal performance of their AI applications. Her linguistics focus before moving into Industry was acoustic sociophonetics, focussing on voice quality variation and turn-taking.

• Judith (Jude) Dineley is a postdoc and member of the Voice and Speech Processing for Health Lab and the Child and Adolescent Mental Health Services Digital Lab at King’s College London. Her work sits at the intersection of speech processing and health. Her current focus is on the evaluation and responsible implementation of clinical AI scribes (ambient voice technology) in child and adolescent mental health services. She also work on clinical studies collecting and analysing speech in mental health disorders, including depression and eating disorders. She started my career as a medical physicist, working clinically and gaining a PhD in Doppler ultrasound.

• Monica Gonzalez Machorro  is working as an AI Researcher at audEERING GmbH and is also doing her PhD at the Technical University of Munich with Professor Björn Schuller. With a background in speech processing and phonetics, her work focuses on analysing speech changes associated with neurological conditions such as multiple sclerosis, aphasia, and amyotrophic lateral sclerosis.

• Odette Scharenborg is a Full Professor of Inclusive Speech Communication at the Delft Inclusive Speech Communication (DISC) group at Delft University of Technology, the Netherlands. Her research aims to develop inclusive speech technology, i.e., making speech technology available for everyone irrespective of how they speak or what language they speak, i.e., including “diverse” speakers and speech. In her research, she considers technical aspects as well as ethical and societal aspects. A particular focus is on child, non-native accented, and pathological speech. From 2017-2025, Odette served on the ISCA Board, where she founded the Diversity committee and served as Vice-president and President (2023-2025). She was the General Chair of Interspeech 2025.

• Priyanka Kommagouni  is an AI Audio Research Engineer at Meeami Technologies, working on speech and audio processing with a focus on developing efficient AI solutions for real-world applications. Her Master’s thesis focused on speech pathology, exploring technology-driven approaches to address challenges in speech and communication. Currently, her Industry work experience involves optimizing and deploying AI audio models on edge platforms with constrained hardware, with an emphasis on computational efficiency, low latency, and practical deployment.

• Sandra Arcos-Holzinger is an Engineer and Machine Learning Researcher with 7+ years of R&D experience in the private and public sectors. In 2025, she returned to academia as a PhD candidate at the University of Melbourne, and a Doctoral Researcher at Johns Hopkins University, CLSP. Her work and research interests are in Signal Processing, Machine Learning and Applied Mathematics with focus on AI robustness and reliability in speech technologies and multimodal settings.

• Shelley Paget is a business development and operations leader in the AI data industry with a background in linguistics. She has a Master of Arts (Research) from the University of Sydney which focused on the acoustic characteristics of lexical stress in Hindi-accented English, born out of practical questions she was facing in her work as a linguist and project manager at Appen.  Over the course of her career, she has managed large customer portfolios, built out business lines & processes, and coordinated cross-functional teams to develop the data that drives speech tech, LLMs, and computer vision.  

• Xi Xuan is a Doctoral Researcher in the Computational Speech Group at the University of Eastern Finland. Her research focuses on efficient, real-time modelling and interpretability for multiple speech-related tasks, including speech deepfake detection, source tracing, and speaker recognition. She also has broader interests in acoustics, language processing, and audio forensics. Previously, she worked in the Department of Linguistics at City University of Hong Kong on a project on machine translation of court judgments, funded by the Hong Kong Research Grants Council. She will be a Visiting Scholar in the Statistical Speech Technology Group at the Beckman Institute for Advanced Science and Technology, University of Illinois Urbana-Champaign.