Extraction of Speech Features and Alignment to Detect Early Dyslexia Evidences

• Published in: Enterprise Information Systems pp. 317 - 335
• Main Authors: Ribeiro, Fernanda M., Pereira, Alvaro R., Paiva, Débora M. Barroso, Alves, Luciana M., Bianchi, Andrea G. Campos
• Format: Book Chapter
• Language: English
• Published: Cham Springer International Publishing
• Series: Lecture Notes in Business Information Processing
• Subjects: Decision making system; Features; Mel cepstral frequencies; Signal processing; Supervised learning
• ISBN: 9783030754174; 3030754170
• ISSN: 1865-1348; 1865-1356
• DOI: 10.1007/978-3-030-75418-1_15

Specific reading disorders are conditions caused by neurological dysfunctions that affect the linguistic processing of printed text. Many people go untreated due to the lack of specific tools and the high cost of using proprietary software; however, new audio signal processing technologies can help identify genetic pathologies. The methodology developed by medical specialists extracts characteristics from the reading of a text aloud and returns evidence of dyslexia. This work proposes an improvement of the research presented in [25], extracting new features and improvements serving as a tool for dyslexia indication efficiently. The analysis is done in recordings of the reading of pre-defined texts with school-age children. Direct and indirect characteristics of the audio signal are extracted. The direct ones are obtained through the methodology of separation of pauses and syllables. Simultaneously, the indirect characteristics are extracted through the alignment of audio signals, the Hidden Markov Model, and some heuristics of improvement. The indication of the probability of dyslexia is performed using a machine learning algorithm. The tests were compared with the specialist’s classification, obtaining high accuracy on the evidence of dyslexia. The difference between the values of the characteristics collected automatically and manually was below 20% for most features. Finally, the results show a promising research area for audio signal processing concerning the aid to specialists in the decision making related to language pathologies.