Germany will start using speech recognition software to identify migrants' country of origin, the Federal Migration Office (BAMF) has declared. The trials for the software will begin in about two weeks and if the system works well, it will be deployed widely in 2018.
Although there are many linguists covering 80 languages at the migration office, a backlog of nearly 430,000 applications of asylum seekers was reported in the beginning of 2017. The agency hopes that implementing the software will ease pressure on the staff and clear out applications faster.
The software is based on voice recognition programs widely used by banks and insurance companies. It is designed to analyse the dialects of refugees based on speech samples.
The results will then be used to determine if an asylum applicant comes from a particularly war-torn region or a conflict zone and is in need of asylum.
Some experts, however, express concern about the accuracy of the software.
"I don't see how automated software can distinguish whether a person uses a certain word or pronounces it in a particular way because this is part of their own repertoire or because they were primed to do so by the interviewer or interpreter," University of Essex linguistics Professor Monika Schmid told Deutsch Welle. "Identifying the region of origin for anyone based on their speech is an extremely complex task. Both humans and machines can easily be wrong, but humans are probably better at realizing this," she added.
Official figures indicate that close to 60% of refugees who entered Germany last year did not have required identification papers. The largest numbers of migrants are from Syria, followed by Afghanistan and Iraq.