Voice Recognition Outperforms Humans In Court
Voice Recognition Outperforms Humans In Court
Voice Recognition Outperforms Humans In Court – A key question in many court cases is whether a speaker on an audio recording is the defendant – new research assisted by Australian experts suggests voice recognition can help.
In most English-speaking countries, expert testimony is only admissible in a court of law if it will potentially assist the judge or the jury to decide. If the judge or the jury’s speaker identification were equally accurate, or more accurate than a forensic scientist’s forensic voice comparison, then the forensic-voice-comparison testimony would not be admissible.
In a research paper ‘Speaker identification in courtroom contexts – Part 1’, published in the journal, Forensic Science International, a multidisciplinary international team of researchers has reported the first set of results from a comprehensive study.
The study compares the accuracy of speaker identification by individual listeners (judges or jury members) with the accuracy of a forensic-voice-comparison system based on state-of-the-art automatic-speaker-recognition technology using recordings that reflect the conditions of an actual case.
The recording was of a telephone call with background office noise, and the known speaker recording was of a police interview conducted in an echoey room with background ventilation-system noise. The forensic-voice-comparison system performed better than all the 226 listeners tested.
The research team was made up of forensic data scientists, legal scholars, experimental psychologists, and phoneticians, based in the UK, Australia, and Chile.
“Past experiences where we have successfully recognized familiar speakers, such as family members or friends, can lead us to believe that we are better at identifying unfamiliar voices than we really are,” said contributing author, Dr Kristy A Martire, School of Psychology, University of New South Wales.
“This study shows that whatever ability a listener may have in recognizing familiar speakers, their ability to identify unfamiliar speakers is unlikely to be better than a forensic-voice-comparison system.”
According to Professor Gary Edmond, School of Law, University of New South Wales, unequivocal scientific findings are that “identification of unfamiliar speakers by listeners is unexpectedly difficult and much more error-prone than judges and others have appreciated”.
“We should not encourage or enable nonexperts, including judges and jurors, to engage in unduly error-prone speaker identification,” Dr Edmond said. “Instead, we should seek the services of real experts: specialist forensic scientists who employ empirically validated and demonstrably reliable forensic-voice-comparison systems.”
Meanwhile, corresponding author, Dr Geoffrey Stewart Morrison, director of the Forensic Data Science Laboratory at Aston University, said that a few years ago, when testifying in a court case, he was asked by a lawyer why the judge couldn’t just listen to the recordings and make a decision – wouldn’t the judge do better than the forensic-voice-comparison system that he had used?
“That was the spark that led to us conducting this research,” Dr Aston said. “I was expecting our forensic-voice-comparison system to perform better than most of the listeners, but I was surprized when it performed better than all of them. I’m happy that we now have such a clear answer to the question asked by the lawyer.”
#SEN #SENnews #security #electronics
