Empirical test of the performance of an acoustic-phonetic approach to forensic voice comparison under conditions similar to those of a real case

In a New South Wales, Australia, case that went to trial in 2012, the defendant was accused of lodging fraudulent tax returns via the Australian Tax Office’s automated telephone system. The system verbally asked the caller questions using a synthesized or pre-recorded voice, and used automatic speech recognition to interpret the caller’s spoken responses. The system also recorded the outgoing and incoming audio. A suspect was questioned in a police interview room, and that interview was recorded.

from #AlexandrosSfakianakis via Alexandros G.Sfakianakis on Inoreader http://ift.tt/2pIiJpu
via IFTTT