A Classification Method of Children with Developmental Dysphasia Based on Disorder Speech Analysis
The result's identifiers
Result code in IS VaVaI
<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F68407700%3A21230%2F08%3A03145878" target="_blank" >RIV/68407700:21230/08:03145878 - isvavai.cz</a>
Result on the web
—
DOI - Digital Object Identifier
—
Alternative languages
Result language
angličtina
Original language name
A Classification Method of Children with Developmental Dysphasia Based on Disorder Speech Analysis
Original language description
This paper focuses on method developed for classifications of the speech with disorders. We are interested in children's neurolog- ical disorder called developmental dysphasia and its in uence on the speech. Described clasification method is based on children's speech sig- nal analysis and allows observing the trend of the speech disorder during therapy. The classification is based on the fact that the disorder has an direct impact on speech production (i.e. movement of vocal tract). Thus, we can measure the trend of the disorders comparing patterns obtained from speech of healthy children to the patterns obtained from children with disorder. Described method is based on cluster analysis of Koho- nen Self-Organizing Maps (KSOMs) trained on speech signals. The main advantage of using artificial neural network is adaptability to specific at- tributes of the signal and tolerance for the noise contained in recordings.
Czech name
Metody klasifikace dětí s vývojovou dysfázií založené na analýze narušené řeči
Czech description
Příspěvek je zaměřen na vývoj metod určených pro klasifikaci řeči s vadami. Jedná se konkrétně o neurologickou poruchu nazvanou vývojová dysfázie. Popisovaná metoda je založena na analýze a sledování trendu poruchy během terapie. Klasifikace je založenana přímé souvislosti nemoci a řečového projevu. Řečové projevy jsou porovnávány s řečí zdravých dětí v kontrolní skupině. Metoda je založena na Kohonenových SOM, které jsou, mimo jiné, odolné vůči šumu.
Classification
Type
D - Article in proceedings
CEP classification
JA - Electronics and optoelectronics
OECD FORD branch
—
Result continuities
Project
<a href="/en/project/GD102%2F08%2FH008" target="_blank" >GD102/08/H008: Analysis and modelling biomedical and speech signals</a><br>
Continuities
Z - Vyzkumny zamer (s odkazem do CEZ)
Others
Publication year
2008
Confidentiality
S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů
Data specific for result type
Article name in the collection
Artificial Neural Networks - ICANN 2008
ISBN
978-3-540-87558-1
ISSN
0302-9743
e-ISSN
—
Number of pages
7
Pages from-to
—
Publisher name
Springer
Place of publication
Heidelberg
Event location
Prague
Event date
Sep 3, 2008
Type of event by nationality
EUR - Evropská akce
UT code for WoS article
000259567200085