Stuttering is a speech disorder which is characterized by blocks, prolongations, and repetitions of words, and syllables. It has a prevalence of about 1% of the population. The condition is treatable but not curable. Good results in therapy can be achieved by teaching a 1technique called “Fluency Shaping”. One institute in Germany that oers this kind of therapy is our project partner Kasseler Stottertherapie (KST).
The research project is based in the area of machine learning and pattern recognition. Recognizing stuttering events is a hard medical problem. To recognize such events, methods from pattern recognition and machine learning are being used, colloquially labeled as artificial intelligence, to enable automatic detection. To achieve this medical expert knowledge as well as deep learning methods are combined to dierentiate between fluent speech, repetitions, blocks and unnatural prolongations as well as detecting if a client is using the speech technique learned during therapy.
As speech data is highly sensible personal data it is of utmost importance to guarantee peoples privacy. To ensure this all algorithms developed must be adapted to run on smartphones
or smart-health devices. This is supposed to guarantee data privacy by not sending speech data into the cloud, as it is usually done for speech analysis. To enable this algorithms must
be adapted to be performance and energy eicient on devices with limited resources.
A main goal of this research is to be able to successfully classify stuttering events on devices with limited resources. My research is supposed to lay the foundation for technical aids that
can be used in stuttering therapy, but can in part be transferable to other speech disorders and pathologies. This shall enable a lasting control of therapy success.
Non obstructive monitoring of speech and voice disorders with a special regard to privacy
MEMBER IN THE JOINT ACADEMIC PARTNERSHIP
since
Prof. Dr.-Ing. Korbinian Riedhammer
Project:
Non obstructive monitoring of speech and voice disorders with a special regard to privacy
Publikationen
Baumann, I., Bayerl, S. P., Bocklet, T., Braun, F., Riedhammer, K. & D. Wagner (2023):
Medical Speech Processing for Diagnosis and Monitoring: Clinical Use Cases. DAGA, Hamburg.
Bayerl, S. P., Gerczuk, M., Batliner, A., Bergler, C., Amiriparian, S., Schuller, B., Nöth, E. & K. Riedhammer (2023):
Classification of Stuttering – The ComParE Challenge and Beyond. Computer Speech & Language 81, 101519.
Bayerl, S. P., Wagner, D., Baumann, I., Bocklet, T. & K. Riedhammer (2023):
Detecting Vocal Fatigue with Neural Embeddings. Journal of Voice.
Bayerl, S. P., Wagner, D., Baumann, I., Hönig, F., Bocklet, T., Nöth, E. & K. Riedhammer (2023):
A Stutter Seldom Comes Alone – Cross-Corpus Stuttering Detection as a Multi-Label Problem, Proc. INTERSPEECH 2023. Dublin, pp. 1538–1542.
Hintz, J., Bayerl, S. P., Sinha, Y., Ghosh, S., Stober, S., Riedhammer, K. & I. Siegert (2023):
Anonymization of Stuttered Speech – Removing Speaker Information while Preserving the Utterance. ISCA SPSC, Dublin.
Hintz, J., Sinha, Y., Bayerl, S. P., Riedhammer, K. & I. Siegert (2023):
Impact of Pathological Speech on Speaker Anonymization - A Proof of Concept. DAGA, Hamburg.
Pérez-Toro, P.A., Rodríguez-Salas, D., Arias-Vergara, T., Bayerl, S. P., Klumpp, P., Riedhammer, K., Schuster, M., Nöth, E., Maier, A. & J. R. Orozco-Arroyave (2023):
Transferring Quantified Emotion Knowledge for the Detection of Depression in Alzheimer’s Disease Using Forestnets, International Conference on Acoustics, Speech and Signal Processing (ICASSP), IEEE, Rhodes Island, Greece.
Bayerl, S. P., Wagner, D., Nöth, E., Bocklet, T. und K. Riedhammer (2022):
The Influence of Dataset Partitioning on Dysfluency Detection Systems, in: P. Sojka, I. Kopeček, K. Pala, A. Horák (Hrsg.): Text, Speech, and Dialogue. Basel: Springer International Publishing.
Bayerl, S. P., Roccabruna, G., Chowdhury, S. A., Ciulli, T., Danieli, M., Riedhammer, K. und G. Riccardi (2022):
What Can Speech and Language Tell Us About the Working Alliance in Psychotherapy. In: Proc. Interspeech 2022, 2443–2447. doi.org/10.21437/Interspeech.2022-347.
Bayerl, S. P., Wagner, D., Noeth, E. und K. Riedhammer (2022):
Detecting Dysfluencies in: Stuttering Therapy Using Wav2vec 2.0. In: Proc. Interspeech 2022, ISCA, 2022, 2868–2872. doi.org/10.21437/Interspeech.2022-10908.
Bayerl, S. P., Wolff von Gudenberg, A., Hönig, F., Noeth, E. und K. Riedhammer KsoF (2022):
The Kassel State of Fluency Dataset -- A Therapy Centered Dataset of Stuttering. In: Proceedings of the language resources and evaluation conference, European Language Resources Association, 1780–1787.
Braun, F., Erzigkeit, A., Lehfeld, H., Hillemacher, T., Riedhammer, K. und S. P. Bayerl (2022):
Going Beyond the Cookie Theft Picture Test: Detecting Cognitive Impairments Using Acoustic Features, in: P. Sojka, I. Kopeček, K. Pala, A. Horák (Hrsg.): Text, Speech, and Dialogue. Basel: Springer International Publishing.
Schuller, B., Batliner, A., Amiriparian, S., Bergler, C., Gerczuk, M., Holz, N., Larrouy-Maestri, P., Bayerl, S., Riedhammer, K., Mallol-Ragolta, A., Pateraki, M., Coppock, H., Kiskin, I., Sinka, M. und S. Roberts (2022):
The ACM Multimedia 2022 Computational Paralinguistics Challenge: Vocalisations, Stuttering, Activity, & Mosquitoes. In: Proceedings of the 30th ACM international conference on multimedia; MM ’22; Association for Computing Machinery: New York, 7120–7124. doi.org/10.1145/3503161.3551591.
Tammewar, A., Braun, F., Roccabruna, G., Bayerl, S., Riedhammer, K. und G. Riccardi (2022):
Annotation of Valence Unfolding in Spoken Personal Narratives. In: Proceedings of the language resources and evaluation conference, European Language Resources Association: Marseille, 7004–7013.
Regelmäßiger BLOG:
https://sebastianbayerl.de/
Bayerl S. P., Tammewar A., Riedhammer K. und G. Riccardi (2021):
Detecting emotion carriers bycombining acoustic and lexical representations.
In: Proc. ASRU 2021, IEEE Automatic Speech Recognition and Understanding Workshop (ASRU).
Klumpp P., Bocklet T., Arias-Vergara T., Vasquez-Correa J., Perez-Toro P., Bayerl S. P., Orozco-Arroyave J. und E. Nöth (2021):
The Phonetic Footprint of Covid-19? In: Proc. Interspeech 2021, S. 441–445.
Perez-Toro P., Bayerl S. P., Arias-Vergara T., Vasquez-Correa J., Klumpp P., Schuster M., Nöth E., Orozco-Arroyave J. und K. Riedhammer (2021):
Influence of the interviewer on the automatic assessment of alzheimer’s disease in the context of the ADReSSo challenge. In: Proc. Interspeech 2021, S. 3785–3789.
Bayerl S. P., Hönig F., Reister J. und K. Riedhammer (2020):
Towards Automated Assessment of Stuttering and Stuttering Therapy, in International Conference on Text,
Speech, and Dialogue, [Online]. Available at: https://arxiv.org/abs/2006.09222.
Bayerl S. P., et al. (2020):
Offline Model Guard: Secure and Private ML on Mobile Devices,
in 23. Design, Automation and Test in Europe Conference (DATE ’20).
Orozco-Arroyave J.R., et al. (2020):
Apkinson: the smartphone application for telemonitoring Parkinson’s patients through speech, gait and hands movement. In: Neurodegenerative Disease Management, 10 (3), S. 137-157
Bayerl S. P., Riedhammer K. (2019):
A Comparison of Hybrid and End-to-End Models
for Syllable Recognition, in International Conference on Text, Speech, and Dialogue, pp. 352–360 [Online]. Available at: https://arxiv.org/abs/1909.1223.
Wenninger M., Bayerl S. P., Schmidt J. and K. Riedhammer (2019):
Timage–A Robust. Time Series Classification Pipeline, in International Conference on Artificial Neural
Networks, pp. 450–461 [Online]. Available at: https://arxiv.org/abs/1909.09149.
Vásquez-Correa J. C. et al. (2019):
Apkinson: A Mobile Solution for Multimodal Assessment
of Patients with Parkinson’s Disease, Proc. Interspeech 2019, pp. 964–965.
Vorträge und Präsentationen
Bayerl S. P., Wenninger M., Schmidt J., von Gudenberg J. W. und K. Riedhammer (2021):
STAN: A stuttering therapy analysis helper, IEEE Spoken Language Technology Workshop (SLT).
Poster
Bayerl S. P., et al. (2019):
Privacy-preserving speech processing via STPC and TEEs.
