Interactive Voice Technology: Variations in the Vocal Utterances of Speakers Performing a Stress-Inducing Task

摘要

Acoustical analyses were conducted of words produced by four speakers in a motion stress-inducing situation. The aim of the analyses was to document the kinds of changes that occur in the vocal utterances of speakers who are exposed to motion stress and to comment of the implications of these results for the design and development of voice interactive systems. The speakers differed markedly in the types and magnitudes of the changes that occurred in their speech. For some speakers, the stress-inducing experimental condition caused an increase in fundamental frequency, changes in the pattern of vocal fold vibration, shifts in vowel production and changes in the relative amplitudes of sounds containing turbulence noise. All speakers showed greater variabilty in the experimental conditon than in more relaxed control situation. The variability was manifested in the acoustical characteristics of individual phonetic elements, particularly in speech sound variability observed serve to unstressed syllables. The kinds of changes and variability observed serve to emphasize the limitations of speech recogniton systems based on template matching of patterns that are stored in the system during a training phase. There is need for a better understanding of these phonetic modifications and for developing ways of incorporating knowledge about these changes within a speech recognition system.