Subscribe now

Japan’s national phone company, NTT, has developed a voice-recognition system
that can analyse sentences as they are spoken. Conventional systems wait until
the end of a sentence before analysing it, which leads to delays. NTT says its
system can also tell from the inflection of the voice whether someone is making
a statement or asking a question. It plans to use the system for
ticket-reservation and information retrieval services.

Sign up to our weekly newsletter

Receive a weekly dose of discovery in your inbox. We'll also keep you up to date with New Scientist events and special offers.

Sign up

Popular articles

Trending New Scientist articles

Piano Exit Overlay Banner Mobile Piano Exit Overlay Banner Desktop