Latest in Gear

Image credit: AP Photo/Altaf Qadri

Microsoft AI creates realistic speech with little training

It works in part like the human brain.
728 Shares
Share
Tweet
Share
Save

Sponsored Links

AP Photo/Altaf Qadri

Text-to-speech conversion is becoming increasingly clever, but there's a problem: it can still take plenty of training time and resources to produce natural-sounding output. Microsoft and Chinese researchers might have a more effective way. They've crafted a text-to-speech AI that can generate realistic speech using just 200 voice samples (about 20 minutes' worth) and matching transcriptions.

The system relies in part on Transformers, or deep neural networks that roughly emulate neurons in the brain. Transformers weigh every input and output on the fly like synaptic links, helping them process even lengthy sequences very efficiently -- say, a complex sentence. Combine that with a noise-removing encoder component and the AI can do a lot with relatively little.

The results aren't perfect with a slight robotic sound, but they're highly accurate with a word intelligibility of 99.84 percent. More importantly, this could make text to speech more accessible. You wouldn't need to spend much effort to get realistic voices, putting it within reach of small companies and even amateurs. This also bodes well for the future. Researchers hope to train on unmatched data, so it might require even less work to create realistic dialogue.

All products recommended by Engadget are selected by our editorial team, independent of our parent company. Some of our stories include affiliate links. If you buy something through one of these links, we may earn an affiliate commission.
Comment
Comments
Share
728 Shares
Share
Tweet
Share
Save

Popular on Engadget

Engadget's Guide to Privacy

Engadget's Guide to Privacy

View
Disney+ public pre-orders are open, but without deep bundle discounts

Disney+ public pre-orders are open, but without deep bundle discounts

View
Facebook's Libra currency will get half its backing from the US dollar

Facebook's Libra currency will get half its backing from the US dollar

View
AMD delays 16-core Ryzen 9 CPU to November

AMD delays 16-core Ryzen 9 CPU to November

View
Erica's modular synth helps you make music with preset cards

Erica's modular synth helps you make music with preset cards

View

From around the web

Page 1Page 1ear iconeye iconFill 23text filevr