Speech recognition systems struggle to understand African American Vernacular English (AAVE).
A startup called Speechmatics has developed a technique that appears to reduce this data gap.
In comparison, the systems developed by Google and Amazon both recorded an accuracy of only 68.6%.
It’s free, every week, in your inbox.
Speechmatics attributed much of its performance to a technique called self-supervised learning.
As a result, they can enable AI systems to learn from a much larger pool of information.
This helped Speechmatics increase its training data from around 30,000 hours of audio to around 1.1 million hours.
Learning like a child
One of the techniques benefits was closing Speechmatics age understanding gap.
Based on the open-source projectCommon Voice,the software had a92% accuracy rate on childrens voices.
The Google system, by comparison, had an accuracy of 83.4%.
He leads our coverage of European tech and oversees our talented team of writers.
Away from work, he e(show all)Thomas is the managing editor of TNW.
He leads our coverage of European tech and oversees our talented team of writers.
Away from work, he enjoys playing chess (badly) and the guitar (even worse).
