Speech Signal Analysis of Autistic Children Based on Time-Frequency Domain Distinguishing Feature Extraction

With the rise of Autism Spectrum Disorders (ASD) incidence rate, a new screening method that is capable of diagnosing ASD in a more accurate and convenient way is urgently needed. Unlike traditional scales, electroencephalogram (EEG), and eye movement based methods, the acoustic analysis based method has inherent advantages in data collection and rich algorithms that can be employed in speech processing. In this paper, three methods are compared for the construction of acoustic features based on time-frequency independent component analysis (TF-ICA): (1) extracting and combining the rows of the unmixing matrix of each frequency point to build the feature vector; (2) using the separation results of each frequency point as time-frequency feature; (3) extracting time-domain features from the outputs of TF-ICA. Finally, the features are compared by a deep learning classifier on an ASD speech dataset. It is concluded from the experimental results that method 1 obtained the hiehest recognition rate of 98.51%.