Computer-Assisted Syllable Complexity Analysis of Continuous Speech as a Measure of Child Speech Disorders

Area of Science:

• Speech-language pathology
• Computational linguistics
• Child development

Background:

• Reduced articulation of complex syllables is a common indicator of speech production disorders in children.
• Traditional phonetic transcription is labor-intensive, limiting analysis of large speech samples.
• Automated analysis methods are needed for efficient clinical assessment.

Purpose of the Study:

• To introduce and evaluate a computer-assisted method, Automatic Syllabic Cluster Analysis (ASCA).
• To assess ASCA's effectiveness in broad transcription, segmentation, and counting of syllabic units.
• To determine if syllabic cluster count is a significant indicator of speech disorders in children.

Main Methods:

• Development of the Automatic Syllabic Cluster Analysis (ASCA) tool.
• Application of ASCA for broad transcription, segmentation, and counting of syllabic units in child speech samples.
• Comparison of syllabic cluster counts between children with and without speech disorders.

Main Results:

• ASCA enables fast analysis of speech precision.
• The number of syllabic clusters per utterance was found to be a significant indicator of speech disorder.
• ASCA facilitates broader clinical analysis of continuous speech samples.

Conclusions:

• Automatic Syllabic Cluster Analysis (ASCA) is an effective tool for analyzing syllabic complexity in child speech.
• ASCA provides a significant indicator for identifying speech production disorders.
• This method overcomes limitations of traditional phonetic transcription for large-scale analysis.