Data Mining of Children´s Speech by Growing Hierarchical Self-Organizing Map
The result's identifiers
Result code in IS VaVaI
<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F68407700%3A21230%2F06%3A00126098" target="_blank" >RIV/68407700:21230/06:00126098 - isvavai.cz</a>
Result on the web
—
DOI - Digital Object Identifier
—
Alternative languages
Result language
angličtina
Original language name
Data Mining of Children´s Speech by Growing Hierarchical Self-Organizing Map
Original language description
The subject of the contribution is one of application of KSOM in medical research. It behaves about of parts of the project finding connectivity between neurological disorders of children - developmental dysphasia and assessment of the degree of perception and impairment of speech. Our research is based on classification solved by SSOM with using phonetics knowledge. We use this approach for neural network ability to recognize relevant and irrelevant information about speech and minor noise dependence.The SSOM combines aspects of a vector quantization method with a topology-preserving ordering of the quantization vectors. Children speech database is away complemented. It must bee structed according to age and gender. The submitted maps trained by input data of 6 years old healthy children were compared with the input data of 6 patients observed befor and after first portion medical therapy. The assumed difference in Recognition Rate between both records was proved true.
Czech name
—
Czech description
—
Classification
Type
D - Article in proceedings
CEP classification
JA - Electronics and optoelectronics
OECD FORD branch
—
Result continuities
Project
<a href="/en/project/NR8287" target="_blank" >NR8287: Computer analyses of speech and overnight EEG in children</a><br>
Continuities
P - Projekt vyzkumu a vyvoje financovany z verejnych zdroju (s odkazem do CEP)
Others
Publication year
2006
Confidentiality
S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů
Data specific for result type
Article name in the collection
Digital Technologies 2006 - 3rd International Workshop
ISBN
80-8070-637-9
ISSN
—
e-ISSN
—
Number of pages
6
Pages from-to
—
Publisher name
Žilinská universita, Elektrotechnická fakulta
Place of publication
Žilina
Event location
Žilina
Event date
Dec 1, 2006
Type of event by nationality
WRD - Celosvětová akce
UT code for WoS article
—