Title :
Effect of alcohol on suprasegmental features of voice
Author :
Wakista, Ganesh W. ; Abhayarathne, Sachie J. ; Mendis, Gihan T. ; Arunatileka, Shiromi M. K. D. ; Sandaruwan, K. Damitha ; Gunawardena, Sameera A. ; Fernando, Ravindra
Author_Institution :
Sch. of Comput., Univ. of Colombo, Colombo, Sri Lanka
Abstract :
The effects of alcohol vary from individual to individual. Since motor co-ordination is impaired under intoxication, it affects an individual´s speech production. One of the common questions which arise is; whether is it possible to detect whether a person is intoxicated by observing their speech patterns and if so can it be used to determine the degree of intoxication? To test this hypothesis, healthy male native Sinhala speakers were carefully sorted out. Speech recordings and associated Breath Alcohol Concentration (BrAC) levels were taken under sober and intoxicated condition. The suprasegmental features of the audio recordings such as Fundamental frequency (F0), duration, jitter, shimmer, etc. were analysed. The collected samples were categorized into five evenly distributed ranges according to their BrAC level in order to identify behaviour of suprasegmental features at different BrAC ranges. The extracted features were statistically analysed by calculating the median and quarter-quintile distance for each speaker. Several statistically significant changes were found for increasing intoxication; primary results include increased F0, decreased intensity, and increased voiced to unvoiced ratio, etc. Finally, although it may be concluded that certain changes in speech suprasegmentals will occur as a function of increasing intoxication, these patterns cannot be viewed as universal since a few subjects exhibited no or negative changes.
Keywords :
audio recording; feature extraction; medical disorders; pneumodynamics; speech; speech processing; statistical analysis; audio recordings; breath alcohol concentration levels; motor co-ordination impairement; speech patterns; speech recordings; statistical analysis; voice suprasegmental feature extraction; Accidents; Acoustics; Blood; Feature extraction; Forensics; Jitter; Speech; Alcohol Intoxication; Breath Alcohol Concentration; Forensic Medicine; Suprasegmental Features;
Conference_Titel :
Information and Communication Technologies (WICT), 2014 Fourth World Congress on
Print_ISBN :
978-1-4799-8114-4
DOI :
10.1109/WICT.2014.7077277