More than one in four people currently integrate speech recognition into their daily lives. A new algorithm developed by a University of Copenhagen researcher and his international colleagues ...

Researchers at the University of Toronto have pioneered a method of developing on-device speech recognition models that achieve state-of-the-art accuracy.

Google has created an offline speech recognition system that is faster and more accurate than a comparable system connected to the Internet. While research papers are usually very theoretical ...

The only feature that doesn’t work offline, however, is the new speech-recognition tool because the actual speech recognition is handled by Duolingo’s servers.

That victory required highly computationally-efficient AI rather than just brute force, something Google thinks could help it move speech recognition offline.

Google’s latest speech recognition works entirely offline, eliminating that delay altogether — though of course mangling is still an option.