Accent bias: AI models penalize certain speakers in interviews and tests, UW study finds
· geekwire.com · popularity 21/100 · 0 similar stories today · Biology & Life Sciences (Science)
Read the original at geekwire.com →
Summary
Models from Google and OpenAI scored American and British speakers higher than Chinese and Nigerian speakers, even when everyone read the same script. Read More
Found in: GeekWire. Rating basis: single outlet; outlet tier 2 (unlisted); 1 feeds; feed position 1.