ИСТИНА

This paper discusses the results of experimental researches in the eld of auditory recognition of speech semantic content on the basis of Russian spoken discourses in noise. In the analysis some spoken discourses in noise were oered to listeners for auditory perception and then recognition of main topics and subtopics of the stimuli. In speech perception researches a listener is usually considered a decoder of sounds and syllables. The listeners were supported to respond to questions about speech fragments or prosody of utterances. These experiments are relatively simple. More difficult is the task of speech signals recognition regarding intelligibility in noise, and most dicult are experiments on perceptual recognition and understanding of semantic content (topics and subtopics) of speech flow in noise. And our aim was to investigate the possibility of auditory recognition of the third type of researches. In this pilot research a new aspect of the problem of speech recognition and understanding was considered in noise regarding Russian spoken discourses. The research included the following questions: a) is it possible to dene topics and subtopics of spoken discourse in noise; b) does the quality of speech recognition and understanding depend on a subject of spoken discourse; c) how do these factors correlate. The statistical analysis revealed that there is a main eect of the seman- tic content recognition of spoken text/discourse in noise (some kinds of signal-noise ratio) by listeners.