Notes on phonological based drunken detection algorithm

In this paper we propose a new algorithm for detecting if a person is under the influence of alcohol. This algorithm is based on number of pauses the speaker makes by judging that if the number of pauses compared to the previous recordings of the same person, which has been recorded beforehand, is higher. If so the algorithm mark the speaker as drunk. 1 Past works There are numerous researches conducted on effects of alcohol, all suggesting fundamental frequency and speech duration are among top factors that change while being intoxicated is the duration of speech i.e. number of pauses. a. Number of pauses Tisljár-Szabó et al (2014), Braun et al (2003) all suggest that the number of pauses will increase while being under influenced. Braun (2003) recorded 33 male subject's speech. He then calculated the total duration of the utterances before and after being intoxicated. Below is the chart from Braun (2003).