SPEECH ANALYSIS OF CHILDREN WITH SPECIFIC LANGUAGE IMPAIRMENT
The result's identifiers
Result code in IS VaVaI
<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F68407700%3A21230%2F15%3A00225569" target="_blank" >RIV/68407700:21230/15:00225569 - isvavai.cz</a>
Result on the web
<a href="http://www.journals.elsevier.com/biomedical-signal-processing-and-control" target="_blank" >http://www.journals.elsevier.com/biomedical-signal-processing-and-control</a>
DOI - Digital Object Identifier
—
Alternative languages
Result language
angličtina
Original language name
SPEECH ANALYSIS OF CHILDREN WITH SPECIFIC LANGUAGE IMPAIRMENT
Original language description
Specific Language Impairment (SLI) is frequent and serious neurodevelopmental impairment of speech analysis and production. SLI is a language disorder that is usually diagnosed in early childhood. The aim of this case-control study was to compare the speech signal analysis between children with SLI and the controls, i.e., healthy children. Databases with a comparative corpus for the children with SLI and the controls were created. The texts of the recorded utterances were composed by speech therapists and clinical psychologists. Logistic regression confirmed that the longer duration of the utterances were significantly associated with a higher risk of SLI. As indicated by K-means cluster analysis, the duration of the utterances were also correlated with the degree of severity of SLI that was defined by a speech therapist. One of the Artificial Neural Network (ANN) techniques, called Self-Organizing Maps (SOM), was used for a vowel analysis and a visualization of the highly dimensional speech data. The results of these analyses created a basis that allowed for the patients to be split into three groups. The replacement of vowels in the so-called vocalic triangle (based on formant analysis) is already a characteristic of this disorder. Systematic and profound analysis of the signals of children’s speech could complement the analysis of the logopaedical, psychological and electrophysiological manifestation of children with SLI.
Czech name
—
Czech description
—
Classification
Type
O - Miscellaneous
CEP classification
JA - Electronics and optoelectronics
OECD FORD branch
—
Result continuities
Project
<a href="/en/project/NT11443" target="_blank" >NT11443: Computer analysis of speech expression, EEG records and MR tractography in children with developmental dysphasia</a><br>
Continuities
P - Projekt vyzkumu a vyvoje financovany z verejnych zdroju (s odkazem do CEP)
Others
Publication year
2015
Confidentiality
S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů