Specialized systems that have performed better than international services—including Google’s speech recognition system—in comparative evaluations.
However, the new-developed technology has outperformed leading international services, including Google’s speech recognition system, in comparative evaluations.
It is designed specifically to address the challenges of Persian speech recognition in telephone-based communication environments.
The technology was developed by Hadi Vaisi, a faculty member at the University of Tehran’s Faculty of Intelligent Systems.
“This technology was developed using several thousand hours of real telephone conversations collected from contact centers across Iran,” Vaisi said.
He added that relying on locally sourced data, including speech samples representing different Iranian dialects and accents, has enabled the system to better adapt to the linguistic characteristics and real-world conditions of telephone conversations in the country.
“This local data gives the system a significant advantage in understanding the way Persian is actually spoken across different regions of Iran,” Vaisi said.
This product is currently being utilized by several organizations within smartphone-based assistant systems and intelligent customer response processes. It contributes to the development of indigenous artificial intelligence infrastructure and the reduction of reliance on foreign technologies; by leveraging independent technology—tailored to the Persian language, its dialects, and local context—it facilitates the creation of intelligent services in Persian.
MNA/7010645
Your Comment