Postagem em destaque

Antologia: Miríade, Distopia, Utopia (2004-2024) -

     Antologia : Miríade, Distopia, Utopia  (2004-2024); @vanres1974; #antologia;  {11dez24 qua 20:40-20:50}      Anthology: Myriad, Dystopi...

Prof. Dr. Vander Resende, Doutorado em Lit Bras, pela UFMG; Mestre em Teorias Lit e Crít Cul, UFSJ

quinta-feira, 2 de abril de 2020

Speech recognition racial bias


02apr20 26-24mar2020

On average, the systems misunderstood
     35 percent of the words spoken by blacks but only
     19 percent of those spoken by whites.

Automated speech recognition less accurate for blacks: study

All five speech recognition technologies had error rates that were almost twice as high for blacks as for whites—even

when the speakers were matched by gender and age and
when they spoke the same words.

Error rates were highest for African American men, and the disparity was higher among speakers who made heavier use of African American Vernacular English.

Hidden bias
The researchers speculate that the disparities common to all five technologies stem from a common flaw—the machine learning systems used to train speech recognition systems likely rely heavily on databases of English as spoken by white Americans. A more equitable approach would be to
include databases that reflect a greater diversity of the accents and dialects of other English speakers.
While the study focused exclusively on disparities between black and white Americans, similar problems could affect people who speak with
  • regional and
  • non-native-English accents,
the researchers concluded.
If not addressed, this translational imbalance could have serious consequences for people's careers and even lives.
  • Many companies now screen job applicants with automated online interviews that employ .
  • Courts use the technology to help transcribe hearings.
  • For people who can't use their hands, moreover, speech recognition is crucial for accessing computers.

Nenhum comentário:

Postar um comentário