Photo: Jose Trangol (UNAM)
A graduate student in the engineering department is developing voice-recognition software for use in investigations and court cases, the National Autonomous University of Mexico, or UNAM, said.
Jose Trangol’s program would help analyze evidence in court cases, where voice recordings are often used to prove a suspect’s innocence or guilt.
“The main point in this project is presenting a methodology for forensic evaluation that is as objective as possible so the system will not be subjective, as is the case now,” Trangol said.
The aim is to determine whether a suspect is the source of the voice on a recording using scientific methods, Trangol said during a seminar sponsored by the UNAM’s Applied Mathematics Research Institute.
The program analyzes the patterns in a voice using statistical benchmarks to determine whether the suspect is the person speaking.
Recordings are currently analyzed using spectrograms that graph the tone and volume of a voice, leaving it up to the judge to weigh the evidence and determine its validity, Trangol said.
The new method uses four data sources - the recording presented to the court, a voice archive of the suspect, a control archive and an archive with the voices of a benchmarking population with the same gender, age, physical condition and mannerisms - to come up with a comparison and produce reliable results.
The project, which is being developed with the assistance of engineering professor Abel Herrera, would make an important contribution to voice analysis in Latin America, where there is a lack of equipment for conducting investigations in an area that is becoming increasingly important around the world, the UNAM said.