Grant: Discovery Grants Program - Individual
University of New Brunswick
$16,330.00
Biomedical speech processing research
EF 2009-10
Résumé
The proposed research focuses on acoustic studies of motor neuron disorders that yield perturbations on the speech produced depending on the location of the lesion in the peripheral or central nervous system. This investigation is based on clinical evidence of a direct correlation between the location of the neurological lesions and the perturbations observed in the produced speech, which enable the determination of unique acoustic patterns that describe the complaints. The neurological disorders that will be studied include amyotrophic lateral sclerosis, multiple sclerosis and Parkinson disease among other neurological impairments. Diagnostic and a detailed characterization of the acoustic perturbations at very early stages of these disorders are important for rehabilitation, treatment and research.
The research program will develop the algorithms and tools required to implement a new methodology to assess the acoustic perturbations perceived from the pathologic speech using automatic instrumental techniques. The research will combine speech processing, pattern recognition and data analysis algorithms to automatically explore all aspects of the speech production mechanism and derive the acoustic perturbations manifested in the recorded utterances that characterize the studied disorders. By automatically classifying the disorders based on the extracted acoustic data and making relevance analyses of the input features, diagnosis and a detailed characterization of the acoustic perturbations will be achieved.
The automatic instrumental approach will overcome the limitations of subjective methods often used in clinical studies for assessing the severity of the speech perturbations and will provide a consistent method of modeling the perception of the acoustic perturbations. Non-linear assessment algorithms will be studied to maximize the classification performance, enable efficient analysis of relevant acoustic dimensions and provide alternative information on the underlying mechanisms relating the studied disorders. This will provide effective paths to improve research and rehabilitation procedures.
Programme
Discovery Grants Program - Individual
Bénéficiaire
Emplacement
New Brunswick, Canada
Type de bénéficiaire
Academia
Type
Grant
Source
NSERC's Awards Data
Tel que publié
Application id
342287-2008
Name nom
CastilloGuerra, Eduardo
Department département
Electrical and Computer Engineering
Organization id
75
Institution établissement
University of New Brunswick
Province en
New Brunswick
Province fr
Nouveau-Brunswick
Country en
CANADA
Country fr
CANADA
Fiscal year exercice financier
2009
Competition year année de concours
2008
Award amount
16330
Program id
RGPIN
Program nane en
Discovery Grants Program - Individual
Program name fr
Programme de subventions à la découverte - individuelles
Group en
Discovery grants programs
Group fr
Programmes de subventions à la découverte
Committee code
335
Committee name en
Electromag. & Electr. Systems (H)
Committee name fr
Électromagn. et syst. électr. (H)
Area of application code
1102
Area of application group en
Health, education and social services
Area of application group fr
Santé publique, éducation et services sociaux
Area of application en
Biomedical engineering
Area of application fr
Génie biomédical
Research subject code
1900
Research subject group en
Biomedical engineering
Research subject group fr
Génie biomédical
Research subject en
Biomedical engineering
Research subject fr
Génie biomédical
Partie
2
Nb partie
5
Application title
Biomedical speech processing research
Keyword
NA
Application summary
The proposed research focuses on acoustic studies of motor neuron disorders that yield perturbations on the speech produced depending on the location of the lesion in the peripheral or central nervous system. This investigation is based on clinical evidence of a direct correlation between the location of the neurological lesions and the perturbations observed in the produced speech, which enable the determination of unique acoustic patterns that describe the complaints. The neurological disorders that will be studied include amyotrophic lateral sclerosis, multiple sclerosis and Parkinson disease among other neurological impairments. Diagnostic and a detailed characterization of the acoustic perturbations at very early stages of these disorders are important for rehabilitation, treatment and research.
The research program will develop the algorithms and tools required to implement a new methodology to assess the acoustic perturbations perceived from the pathologic speech using automatic instrumental techniques. The research will combine speech processing, pattern recognition and data analysis algorithms to automatically explore all aspects of the speech production mechanism and derive the acoustic perturbations manifested in the recorded utterances that characterize the studied disorders. By automatically classifying the disorders based on the extracted acoustic data and making relevance analyses of the input features, diagnosis and a detailed characterization of the acoustic perturbations will be achieved.
The automatic instrumental approach will overcome the limitations of subjective methods often used in clinical studies for assessing the severity of the speech perturbations and will provide a consistent method of modeling the perception of the acoustic perturbations. Non-linear assessment algorithms will be studied to maximize the classification performance, enable efficient analysis of relevant acoustic dimensions and provide alternative information on the underlying mechanisms relating the studied disorders. This will provide effective paths to improve research and rehabilitation procedures.