This research looks at the differences between speech affected by the common cold (""""""""cold-speech"""""""") and normal/healthy speech so that the information can be used for automatic speaker recognition - one of the world's most-exciting emerging technologies. Unlike """"""""personal identify"""""""" technologies like scanning the retina of the eye and taking finger prints, speaker recognition can utilize a piece of equipment that most people already have in their homes - a telephone. Speaker recognition is already being used to confirm that speakers are who they say they are in forensic applications. it is imperative that the technology be able to handle a situation where a speaker can still be recognized if their speech sounds different from their """"""""normal"""""""" voice. Conditions that would considered """"""""different"""""""" from normal are speech signals that reveal that a person is """"""""tired"""""""" or excited."""""""" """"""""Cold-speech' represents a more extreme difference. The goals of the proposed research are: (a) to understand the specific correlations between features used in speaker recognition and changes in the size of the oral, pharyngeal and nasal cavities; (b) to achieve further insight into the significance of physiological parameters defined by the literature nd their role in the sounds that the cold produces; (c) to examine the specific impact of nasal occlusion (stuffy nose) on speaker recognition parameters; and (d) to examine the linguistic elements (changes in vowel and consonant structure) that correspond to a cold. The proposed research will examine characteristics of speech produced under the influence of the common cold. These characteristics, and recommedations for compensation techniques, can be utilized to improve applications in speech technology which currently limit performance to normal/healthy voices. Physiological information from the oral and nasal cavities (characteristics of fluid and air flow), linguistic information involving phonetic and phonological analyses (ie.e. substituting """"""""s"""""""" for """"""""sh"""""""" in the word """"""""she"""""""" during a cold,) and the transformation of speech sounds to mathematical coefficients, are all interconnected. This research will combine the information from three fields; Speech Pathology, Linguistics, and Electrical Engineering to promote inclusion of acute and chronic speech pathologies in state-of-the-art speech technology.
