“Racial Disparities in Automated Speech Recognition.” n.d. https://doi.org/10.1073/pnas.1915768117.

Notes

• More WER for black speakers than white speakers
  • Potential RQ: Is there similar disparity among the Indian users as well? ASR works better for higher income groups than lower income groups? ASR effectiveness across caste groups?

In-text annotations

"In total, this corpus spans five US cities and consists of 19.8 h of audio matched on the age and gender of the speaker. We found that all five ASR systems exhibited substantial racial disparities, with an average word error rate (WER) of 0.35 for black speakers compared with 0.19 for white speakers. We trace these disparities to the underlying acoustic models used by the ASR systems as the race gap was equally large on a subset of identical phrases spoken by black and white individuals in our corpus" (Page 7684)