In the presented work we introduce a new conception, taking advantage of artificial intelligence techniques for analysis of pathological speech, namely the conception of automated understanding, which as we suggest, can be applied to analysis of selected speech pathologies, instead of the more popular approach based on the concept of recognition. The presented concept of the research scheme is based on the technique of advanced acoustic signal analysis and it refers to the analysis of artificial neural networks functioning in the task of recognition of selected types of vocal tract pathologies. It is proposed here that the simple process of signal recognition should be replaced by a more advanced method of its analysis, called the process of understanding of the signal. The method is take advantage of an internal model of the considered signal's generator and it is directed towards such a structure analysis of the examined sound, which enables its identification as a result of cognitive resonance. The described method allowed us to achieve more subtle details for signal characterized by small diversity of measurable parameters, observed for the classes being recognized, what is the case in the problem of identification of selected pathologies considered here. The circumstances mentioned above suggest a consideration of more knowledge-based approach to the discrimination of acoustic signals, described here as a technique of speech signal understanding.
展开▼
