Errattic

Home About Us All Fuctasia_(NSFW) Games Gay+ Health/Food Movies Music Musings Photos_(NSFW) TV Wisps Preferences

Home Page > Current Page


Top Tags

Abuse
Action
All Rights
Art
Asian
Ass
Backlash
Big Balls
Big Cock
Black
Bullying
Business
Celebration
Celebrity
Choices
Cocksuck
Comedy
Community
Compilation
Cum
Daddy Squish
Dance
Drama
Entertainment
Environment
Exhibit
Family
Fantasy
Fear
Feet
Fuck
Funny
Gay
Gear
Giant Cock
Gif
Hairy
Hard
Hate
Health
History
Hole Puncher
Homophobia
Horror
Hostility
Hot Swatch
Hypocrisy
Interracial
Jock
Latin
Legs
Lifestyle
Mass Appeal
Massle
Mat
Mental Health
Muscle
Music
New World Order
Parenting
Piercings
Pillows
Political
Politics
Portrait
Pose
Privilege
Relationships
Religion
Representation
Respect
Romance
Sad
Safety
Science
Self Interest
Sex
Social Media
Sports
Squishy
Support
Sweet
Tats
Threat
Tits
Toned
Toxic
Travel
Treatment
Tribute
Undies
Unity
Video
Violence
Voyeur
Weird
Wet
Women
World
Youth


Login

Create Profile
Login


This site does not claim credit for images, videos, or music, except where noted.


©2020 Errattic.com

Restricted to Adults
This site does not claim credit for images, videos, or music, except where noted.


Welcome to Errattic! We encourage you to customize the type of information you see here by clicking the Preferences link on the top of this page.

 

Personal voice assistants struggle with black voices, new study shows 

 

Speech recognition systems have more trouble understanding black users’ voices than those of white users, according to a new Stanford study.

The researchers used voice recognition tools from Apple, Amazon, Google, IBM, and Microsoft to transcribe interviews with 42 white people and 73 black people, all of which took place in the US. The tools misidentified words about 19 percent of the time during the interviews with white people and 35 percent of the time during the interviews with black people. The system found 2 percent of audio snippets from white people to be unreadable, compared to 20 percent of those from black people. The errors were particularly large for black men, with an error rate of 41 percent compared to 30 percent for black women.

The Verge

Tags: AI, Lifestyle, Race, Recognition, Science, Speak, Tech, Voice

Filed under: Health/Food

24-Mar-2020


Share

Share on Twitter Share on Facebook Share on Google+ Share via Email