The automated telephone call centers companies use to reduce costs can drive customers crazy. A way to spot impatience in callers’ voices-and transfer them to human operators before they hang up-could ease the frustration. Shri Narayanan and Chul Min Lee at the University of Southern California have developed a system that distinguishes irritated from normal speech with up to 85 percent accuracy. Their program identifies specific acoustic features of speech that indicate stress, such as the pitch, energy, and duration of speech sounds, as well as word content and contextual information. The system “learned” what to look for through training on nearly 1,400 real phone calls. The team hopes to improve the software’s accuracy but says it could already benefit companies.
A horrifying new AI app swaps women into porn videos with a click
Deepfake researchers have long feared the day this would arrive.
We can’t afford to stop solar geoengineering research
It is the wrong time to take this strategy for combating climate change off the table.
Meet Altos Labs, Silicon Valley’s latest wild bet on living forever
Funders of a deep-pocketed new "rejuvenation" startup are said to include Jeff Bezos and Yuri Milner.
The new version of GPT-3 is much better behaved (and should be less toxic)
OpenAI has trained its flagship language model to follow instructions, making it spit out less unwanted text—but there's still a way to go.
Get the latest updates from
MIT Technology Review
Discover special offers, top stories, upcoming events, and more.