New approach may open up speech recognition to more languages

Wednesday, December 7, 2016 - 14:31 in Mathematics & Economics

Researchers have developed a new approach to training speech-recognition systems that doesn't depend on transcription. Instead, their system analyzes correspondences between images and spoken descriptions of those images, as captured in a large collection of audio recordings. The system then learns which acoustic features of the recordings correlate with which image characteristics.

Read the whole article on Science Daily

More from Science Daily

Latest Science Newsletter

Get the latest and most popular science news articles of the week in your Inbox! It's free!

Check out our next project, Biology.Net