TE
TechEcho
Home24h TopNewestBestAskShowJobs
GitHubTwitter
Home

TechEcho

A tech news platform built with Next.js, providing global tech news and discussions.

GitHubTwitter

Home

HomeNewestBestAskShowJobs

Resources

HackerNews APIOriginal HackerNewsNext.js

© 2025 TechEcho. All rights reserved.

There Is a Racial Divide in Speech-Recognition Systems, Researchers Say

5 pointsby fvrghlabout 5 years ago

1 comment

downerendingabout 5 years ago
Ugh--this is not a racial problem.<p>Lots of people of all different races--including white--use pronunciation and vernacular that differs significantly from the typical Midwestern speaker. I interact regularly with Caucasians that I can barely understand myself, let alone asking a typical commercial speech recognition system. On the flip side, quite a few black people speak in a manner that is indistinguishable from other races.<p>Universal recognition is the real problem to be solved. We want <i>everyone</i> to be understood.
评论 #22672658 未加载