M. Sigmund and T. Dostal (Czech Republic)
Speech processing, psychological stress, glottal pulses.
This paper deals with speech signals under psychological stress. The investigation of the speaker’s stress is based on statistical analysis of glottal pulses derivative. A pitch synchronous selection of segments from the glottal pulse waveform is used. Selected segments are fixed in their maxima and overlaid. The generated distribution matrix is analysed using special cuts. A new database of speech under stress is created for use in our experiments consisting of data collected during oral final examinations at our university. The database contains read and conversational speech of 31 male speakers, both in neutral and stressed state. The stress recognition rate in the speaker dependent binomial classification (stress/no stress) reaches 88%.
Important Links:
Go Back
