Arabic adaptation of Phonology and Memory test using entropy-based analysis of word complexity

Short-term Phonological Memory evaluation is very important in tracking the learning development of children, and for that, speech-therapists use words with different linguistic complexity levels. The test “Memory and Phonology” (PM) adopted in the Department of Child and Adolescent Neurology in the National Institute of Neurology (Tunisia), relies on a heuristically-constructed database of Tunisian-Arabic words, in analogy with the standardized NEEL PM French test. Given that the choice of a word's phonology is very specific to the language and a costly experimental calibration must be done to validate the classification according to words levels difficulty, this work offers a phonology-based complexity algorithm that validates not only the French data base of the NEEL's test, but also that currently proposed and adopted by the Tunisian speech therapists. The proposed complexity analysis and classification are based on three entropy measures: time-based, spectral, and the variance of dynamic spectral entropy of the sound signal of a given word.