Search
Signal Analysis, Modelling, and Interpretation
Department of Circuit Theory, Technická 2, 166 27 Prague 6
Tel: +420 224 352 236, Fax: +420 233 339 805
http://sami.fel.cvut.cz/
Who we are
doc. Ing. Roman Čmejla, CSc.
head of the group
Ing. Jan Rusz
speech pathology (Parkinson's disease), modeling of physiological signals
Ing. Petr Bergl, PhD.
speech pathology (stuttering, disfluency)
Ing. Petr Ježdík, PhD.
intracranial EEG
Ing. Lukáš Bauer
speech pathology (DSP algorithms)
Ing. Radek Janča
intracranial EEG
Ing. Jan Janda
age dependence of acoustic-phonetic parameters
Ing. Tomáš Lustyk
speech pathology (stuttering and disfluency assessment)
Ing. Martina Nejepsová
speech pathology (developmental dysphasia)
Ing. Adam Stráník
speech pathology (hoarseness)
Ing. Daniel Špulák
physiological signals (multichannel surface EMG)
Bc. Jan Dvořák
speech pathology (implementation of real-time algorithms)
Bc. Michal Novotný
speech pathology (algorithms for evaluation of articulation)
Research description
Research group is concerned with fundamental and applied research in biomedical engineering.
Our main scope of interests focus on the speech, biological signals, digital signal processing and machine learning with background in neurology, phoniatry, speech therapy and physiology.
What is it good for
The findings lead to a deeper understanding and are used in the diagnosis and evaluation of treatment.
Projects
Voice and speech disorders in early Parkinson's disease
Parkinson's disease (PD) is a chronic neurodegenerative disorder characterized by the progressive loss of dopaminergic neurons in the substantia nigra. PD affects people after the age of 50 and is estimated to affect 1.6% of persons over the age of 65; this counts more than 8,000,000 people over the world. Medical treatment, including neuro-pharmacological and neurosurgical methods, alleviates certain symptoms, but there is no causal cure available, and early diagnosis of disease has a vital role in improving the patient's live. Currently, there is an urgent need for cost-effective methods to detect the disease in its early phases, to differentiate it from other diseases, and to monitor its progression and its response to treatment. PD speech can manifest abnormalities related to several aspects including monopitch, monoloudness, imprecise articulation, variability of speech rate, reduced stress, hoarseness, speech disfluencies, inappropriate silence, and others. The purpose of this research is to find whether voice and speech disorders are present from early stages of PD before starting dopaminergic medication, design of novel methods for assessment of PD-related speech features, detect the early signs of PD, and characterize and monitor the disease as it progresses or in response to treatment.
Analysis and processing of intracranial EEG
The epilepsy is a complex chronic neurological disorder characterized by seizures. Thirty percent of people suffering from epilepsy are pharmaco-resistant. Small number of these pharmaco-resistant patients has serious diagnosis that is in the life-threatening state or prevents the development of the children brains. Therefore, neurosurgeons resect a part of damaged brain in order to avoid patients. epileptic seizure. The exact localization of seizure onset zone is essential for successful treatment with minimal or without permanent damage of brain functions. For precise localization of this zone, the methods for analyses of intracranial EEG are used. The aim of the research is to find significant artifact in interictal, ictal and postictal state in time and frequencies domain.
Fluency disorders in people with stuttering
Stuttering is a speech disorder in which the flow of speech is disrupted by involuntary repetitions and prolongations of sound, syllables, word, phrases, and involuntary silent pauses or blocks in which the stutterer is unable to produce sound. Speech dysfluency associated with stuttering is a great social and medical problem. Stuttering is a poorly understood communication disorder with 1% global prevalence; the onset of childhood stuttering is most frequent between a child.s second and fourth birthdays, before decreasing gradually and ultimately affecting nearly 5% of the population. It is widely believed that early identification and treatment of children.s developmental disorders, including stuttering, is the most efficient and effective strategy for preventing such disorders from becoming chronic, long-term disabilities. The project aims is to find methods that would be based on the analysis of stutterers' audio recordings and would be able to objectively and automatically determine the degree of speech fluency disorders. These methods could be useful for phoniatrist experts in determining of stuttering severity.
Age and gender dependence of children speech
An analysis of the relationship between acoustic-phonetic aspects of speech and the speaker.s age may have numerous applications. This research has been motivated by practical experience in the field of phoniatry and logopaedia. When examining children.s pathological speech, there is often an effort to answer the question .What age does particular speech corresponding to., and therefore for example to estimate at what age a child.s speech development stopped. Chronological age is unambiguously given by date of birth. Logopaedic age is the age estimated on the basis of acoustic-phonetic aspects of human speech.
Speech in children with developmental dysphasia
Developmental dysphasia is one of the most common disorders in children.s age, which manifests in different ways - in speech, motoric movement, perception and orientation. The speech development monitoring and subsequent subjective evaluation by pediatricians or phoniatrist is the one of the methods that are used nowadays. The project aims to create an automatic classifier . a software application that would be used to the developmental dysphasia diagnostic.
Large-scale physiological modelling
The research in the area of quantitative model development is currently used as a base for a number of research studies in the field of physiology and physiological modeling, including research on the physiological consequences of weightlessness in manned space flight or in a new approach to automation in medicine. The aim of the research is to build a core model of human physiology based on the original Guyton's diagram targeting the short- and long-time regulation of blood presssure, body fluid and homeostazis of the major solutes. The model can be used for educational purposes and general reflection on physiological regulation in pathogenesis of various diseases.
Multichannel Surface EMG Processing
An electromyogram (EMG) is a recording of electrical activity of muscles. We cooperate with colleagues from the Faculty of Physical Education and Sport (Charles University in Prague). They record surface EMGs during various sport activities. Our analyses are focused on muscle onset detections, muscle coordination analysis during diverse movements and searching for differences between several periods of repeated movement. Muscle fatique detection and assessment of alterations caused by surgeries create parts of our research, too.
Databases, algorithms, tools, support for teaching
These projects encompass the design of novel tools, development of digital signal processing algorithms, creation of freely-accessible databases, real-time applications, educational materials, and among others support for the other projects. The number of signal processing algorithms has been developed in the course of research. These include techniques for speech feature extraction and selection, data visualisation, classification, and regression. The results of this research including novel measurements of articulation, real-time signal processing framework in C#.NET for assessment of speech pathology (automated assessment of /s/, voice field), atlas of voice pathology, collaboration in atlas of physiology and pathophysiology, and many others.
Financial support and contracts
Our research is currently supported by several grants:
- Acoustic voice and speech analysis in patients with central nervous system disorders, Czech Science Foundation GAČR 102/12/2230, R. Čmejla (2012 - 2015)
- Intracranial EEG signal processing; epileptogenic zone identification in non-lesional refractory epilepsy patients Czech Ministry of Health NT11460-4/2010, P. Marusič (2010 - 2013)
- Analysis and Modelling Biomedical and Speech Signals, Czech Science Foundation GAČR GD102/08/H008, R. Čmejla (2008 - 2011)
and also several Ministry of Education and CTU grant and research projects.
International collaboration
We work closely with a number of experts from various institutions, mainly the following:
- 1st Faculty of Medicine, Charles University in Prague
- 2nd Faculty of Medicine, Charles University in Prague
- Faculty of Physical Education and Sport, Charles University in Prague
- School of Clinical & Experimental Medicine, University of Birmingham
- Friedrich-Alexander University Erlangen-Nuremberg
Selected publications
We published several original contributions in the world's leading international scientific journals and presented their results at several international congresses and conferences. Here are just the most important works:
- J. Rusz, R. Čmejla, H. Ružičková, J. Klempíř, V. Majerová, J. Picmausová, J. Roth, and E. Růžička. (2011). "Acoustic assessment of voice and speech disorders in Parkinson.s disease through quick vocal test," Movement Disorders, 26(10): 1951-1952.
- P. Jiruška, P. Marusič, J. G. Jefferys, P. Kršek, R. Čmejla, V. Sebronová, and V. Komárek. (2011). "Sturge-Weber syndrome: a favourable surgical outcome in a case with contralateral seizure onset and myoclonic-astatic seizures," Epileptic Disorders, 13(1): 76-81.
- J. Kofránek, S. Matoušek, J. Rusz, P. Stodůlka, P. Privitzer, M. Mateják, and M. Tribula. (2011). "The Atlas of Physiology and Pathophysiology: Web-Based Multimedia Enabled Interactive Simulations," Computer Methods and Programs in Biomedicine, 104(2): 143-153.
- J. Rusz, R. Čmejla, H. Ružičková, and E. Růžička. (2011). "Quantitative acoustic measurements for characterization of speech and voice disorders in early untreated Parkinson.s disease," Journal of the Acoustical Society of America, 129(1): 350-367.
- J. Kofránek, and J. Rusz. (2010). "Restoration of Guyton´s Diagram for Regulation of the Circulation as a Basis for Quantitative Physiological Model Development," Physiological Research, 59(6): 897-908.
- P. Jiruška, G. T. Finnerty, A. D. Powell, N. Lofti, R. Čmejla, and J. G. Jefferys. (2010). "Epileptic high-frequency network activity in a model of non-lesional temporal lobe epilepsy," Brain, 133(5): 1380-1390.
- P. Jiruška, R. Čmejla, A. D. Powell, W. Ch. Chang, M. Vreugdenhil, and J. G. Jefferys. (2009). "Rerence noise method of removing powerline noise from recorded signals," Journal of Neuroscience Methods, 184(1): 110-114.
- T. Bocklet, E. Noth, G. Stemmer, H. Ruzickova, J. Rusz. (2011) "Detection of Persons with Parkinson's Disease by Acoustic, Vocal, and Prosodic Analysis," in Proceedings of IEEE Automatic Speech Recognition and Understanding Workshop, Hawai.
- R. Janča, P. Ježdík, R. Čmejla, R. Glajcar, P. Kršek, P., A. Jahodová. (2011) "Seizure Onset Zone Detection and Localization in iEEG Using DTF," in Proceedings of IEEE International Symposium on Medical Measurements and Applications, Bari, Italy, p. 93-97.