@inproceedings{BraunBayerlHoenigetal.2024, author = {Braun, Franziska and Bayerl, Sebastian and H{\"o}nig, Florian and Lehfeld, Hartmut and Hillemacher, Thomas and Bocklet, Tobias and Riedhammer, Korbinian}, title = {Infusing Acoustic Pause Context into Text-Based Dementia Assessment}, issn = {2958-1796}, doi = {10.21437/Interspeech.2024-2496}, pages = {1980-1984}, year = {2024}, abstract = {Speech pauses, alongside content and structure, offer a valuable and non-invasive biomarker for detecting dementia. This work investigates the use of pause-enriched transcripts in transformer-based language models to differentiate the cognitive states of subjects with no cognitive impairment, mild cognitive impairment, and Alzheimer's dementia based on their speech from a clinical assessment. We address three binary classification tasks: Onset, monitoring, and dementia exclusion. The performance is evaluated through experiments on a German Verbal Fluency Test and a Picture Description Test, comparing the model's effectiveness across different speech production contexts. Starting from a textual baseline, we investigate the effect of incorporation of pause information and acoustic context. We show the test should be chosen depending on the task, and similarly, lexical pause information and acoustic cross-attention contribute differently.}, language = {en} } @inproceedings{ScheuererHaderleinNoethetal.2021, author = {Scheuerer, Ralph and Haderlein, Tino and N{\"o}th, Elmar and Bocklet, Tobias}, title = {Applying X-Vectors on Pathological Speech After Larynx Removal}, series = {2021 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)}, volume = {2021}, booktitle = {2021 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)}, publisher = {IEEE}, isbn = {978-1-6654-3739-4}, doi = {10.1109/asru51503.2021.9688278}, pages = {1079 -- 1086}, year = {2021}, abstract = {Speaker embeddings extracted from time delayed neural networks (TDNNs) contributed to major recent advancements in speaker recognition and verification. We use an X-Vector system trained on augmented VoxCeleb1 and VoxCeleb2 data to obtain embeddings for pathological speech after total or partial larynx removal. We show that our model is able to effectively distinguish and visualize patient groups when generating embeddings. We further compare various regression models on the task of automatically predicting different perceptual ratings by speech therapists (intelligibility, vocal effort, and overall quality) based on the extracted speaker embeddings. For both patient groups we show Pearson correlations in the range of +0.8; we find that Random Forest and Support Vector Regression produce scores that best resemble the experts' assessments.}, language = {en} } @inproceedings{BraunWitzlErzigkeitetal.2025, author = {Braun, Franziska and Witzl, Christopher and Erzigkeit, Andreas and Lehfeld, Hartmut and Hillemacher, Thomas and Bocklet, Tobias and Riedhammer, Korbinian}, title = {Pitfalls and Limits in Automatic Dementia Assessment}, series = {Interspeech 2025}, booktitle = {Interspeech 2025}, publisher = {ISCA}, issn = {2958-1796}, doi = {10.21437/Interspeech.2025-2280}, pages = {5663 -- 5667}, year = {2025}, abstract = {Current work on speech-based dementia assessment focuses on either feature extraction to predict assessment scales, or on the automation of existing test procedures. Most research uses public data unquestioningly and rarely performs a detailed error analysis, focusing primarily on numerical performance. We perform an in-depth analysis of an automated standardized dementia assessment, the Syndrom-Kurz-Test. We find that while there is a high overall correlation with human annotators, due to certain artifacts, we observe high correlations for the severely impaired individuals, which is less true for the healthy or mildly impaired ones. Speech production decreases with cognitive decline, leading to overoptimistic correlations when test scoring relies on word naming. Depending on the test design, fallback handling introduces further biases that favor certain groups. These pitfalls remain independent of group distributions in datasets and require differentiated analysis of target groups.}, language = {en} }