A multidisciplinary international team of researchers recently reported the first set of findings from a thorough study comparing the accuracy of speaker identification by individual listeners (like judges or jury members) with the accuracy of a forensic voice comparison system based on cutting-edge automatic-speak technology in the research paper “Speaker identification in courtroom contexts — Part I” published in the journal Forensic Science International.
The 226 listeners that were analyzed were outperformed by the forensic-voice-comparison method. The audio of the speaker who was being interrogated was of a phone call with background office noise, and the recording of the speaker who was being known was of a police questioning that took place in an echoing room with background ventilation system noise. The research team included members from the UK, Australia, and Chile as well as forensic data scientists, legal academics, experimental psychologists, and phoneticians.
According to the corresponding author, Dr. Geoffrey Stewart Morrison, and head of the Forensic Data Science Laboratory at Aston University: “Several years ago, during my deposition in a court proceeding, a lawyer questioned me on why the judge couldn’t just listen to the tapes and provide a verdict. The judge surely would do better than the forensic voice comparison method I had employed. That was the catalyst for us to carry out this study.
Story Source: Materials provided by Aston University.
Nabanita Basu, Agnes S. Bali, Philip Weber, Claudia Rosas-Aguilar, Gary Edmond, Kristy A. Martire, Geoffrey Stewart Morrison. Speaker identification in courtroom contexts – Part I: Individual listeners compared to forensic voice comparison based on automatic-speaker-recognition technology. Forensic Science International, 2022; 341: 111499 DOI: 10.1016/j.forsciint.2022.111499
Also Read: Glossary of Speaker Identification and Audio Identification