Conveners
A20.01 Pathological Speech: S145
- Péter Mihajlik (Budapest University of Technology and Economics)
- Martin Hagmüller (Signal Processing and Speech Communication Laboratory)
- Juan Ignacio Godino Llorente
- Melanie Jouaiti
- Julián David Arias Londoño
A20.01 Pathological Speech: P439
- Melanie Jouaiti
- Martin Hagmüller (Signal Processing and Speech Communication Laboratory)
- Juan Ignacio Godino Llorente
- Péter Mihajlik (Budapest University of Technology and Economics)
- Julián David Arias Londoño
-
Niclas Pokel (ETH Zürich)08/09/2026, 13:20A20 Speech
Automatic speech recognition remains unreliable for individuals with impaired speech, in part because a single adapter must absorb the high inter-speaker acoustic variability that characterizes dysarthric, apraxic, and neurodegenerative populations. Parameter-efficient fine-tuning with Low-Rank Adaptation (LoRA), and its Bayesian extension via variational inference (VI-LoRA), can personalize...
Go to contribution page -
Moritz Pfeiler (Signal Processing and Speech Communication Laboratory)08/09/2026, 13:40A20 Speech
The goal of Dysarthric Speech Reconstruction is to improve intelligibility by converting dysarthric into healthy speech. In the future, this technology could become a valuable communication aid for people with this speech impairment. The development of systems performing complex speech tasks typically requires large amounts of data, which is especially sparse for pathological child speech....
Go to contribution page -
Giulia Fusari (University of Milan)08/09/2026, 14:00A20 Speech
Background: Speech production is sensitive to cognitive and affective states. In people with multiple sclerosis (pwMS) with no-to-minimal disability, multidimensional acoustic measures may help characterize subtle variability beyond overt speech disorders.Aim: To explore psychologically related variability in speech measures in pwMS and healthy subjects(HS).Methods: Thirteen pwMS (9females;...
Go to contribution page -
Péter Mihajlik (Budapest University of Technology and Economics)08/09/2026, 14:00A20 Speech
In this study, we evaluate a recently proposed hypernetwork‑based, parameter‑efficient fine‑tuning approach for dysarthric speech recognition in Hungarian and English, using the Whisper ASR (Automatic Speech Recognition) model. We compare its performance to Low‑Rank Adaptation (LoRA) demonstrating the promise of hypernetwork‑driven personalization for atypical ASR. To better understand...
Go to contribution page -
Bernadett Dam (University of Szeged)08/09/2026, 14:00A20 Speech
Motor speech disorders can often lead to reduced intelligibility, communication difficulties, ultimately affecting the person’s quality of life. In recent years, several initiatives have been launched to improve the processing of disordered speech [1]. However, these initiatives differ in their methodology and their degree of success.We are working on a collaborative project called the...
Go to contribution page -
Isabel S. Schiller (Work and Engineering Psychology, RWTH Aachen University)08/09/2026, 14:00A20 Speech
Real-time auditory feedback modulation (AFM) alters how speakers perceive their own voice during speech, enabling the study of vocal motor control. This multiple-case study specifically examines how auditory feedback with artificially increased hoarseness (i.e., hoarseness-induced feedback) affects acoustic voice quality in healthy speakers, relative to two control conditions: unaltered...
Go to contribution page -
Barbara Schuppler (Signal Processing and Speech Communication Laboratory)08/09/2026, 14:00A20 Speech
This paper focuses on the automatic speech recognition (ASR) of speech produced by elderly speakers diagnosed with dementia. In clinical contexts, reliable transcriptions can support the work of clinical linguists and serve as a basis for (automatic) analyses to identify linguistic biomarkers for dementia. ASR is further also increasingly used in voice-based assistive technologies supporting...
Go to contribution page -
Enrique Orozco Olivares (Signal Processing and Speech Communication Laboratory)08/09/2026, 14:00A20 Speech
Pathological speakers whose intelligibility is caused by impairment of vocal fold movement retain largely intact lip and mouth movements, making the visual modality a reliable signal even when the acoustic channel is severely degraded. We propose a multimodal end-to-end voice conversion system that exploits this preserved articulatory information to convert pathological speech into a...
Go to contribution page -
Benedikt Mayrhofer (Signal Processing and Speech Communication Laboratory)08/09/2026, 14:00A20 Speech
Recent advances in self-supervised learning (SSL) have significantly improved speech representations, yet their performance degrades in pathological domains such as electrolaryngeal (EL) speech. Additionally, the large computational footprint of state-of-the-art SSL models limits their applicability in real-time, on-device voice rehabilitation systems. We propose a multi-teacher knowledge...
Go to contribution page -
Anna Viehhauser (Graz University of Technology)08/09/2026, 14:00A20 Speech
Creak is a voice quality frequently occuring in healthy speech, sometimes carrying linguistic or paralinguistic information. Due to the lack of precision in voice control, pathological speakers may produce creak independently from its usual functions. This paper investigates the similarities and differences in temporal characteristics of creak occurences using recordings of German read speech....
Go to contribution page -
Marc Freixes (La Salle, Universitat Ramón Llull)08/09/2026, 14:20A20 Speech
Turner syndrome is a rare chromosomal condition affecting females, characterized by high phenotypic heterogeneity and frequent delays in diagnosis. In recent years, digital health approaches have highlighted the potential of non-invasive biomarkers to support earlier and more accessible screening strategies. Within this context, the BeNeXT project aims to develop scalable diagnostic and...
Go to contribution page