A new Georgia Tech and Stanford study shows automatic speech recognition (ASR) models, used in voice assistants like Amazon Alexa, may not be as accurate when transcribing English speakers with a minority dialect. However, the study found the transcription of Standard American English (SAE) "significantly outperformed" three dialects: Spanglish, Chicano English and African American Vernacular English. We revisit Rose’s conversation with Camille Harris, PhD candidate in computer science at Georgia Institute of Technology, and lead author of the study. Harris discusses some of the key findings from her study. 

Plus, Elizabeth J. West, a professor of English and co-director of Georgia State University’s Center for Studies on Africa and Its Diaspora, and her research partners, Dr. Joshua Jackson and John Washington discuss a mapping project that could be used to reveal the locations of where more than 5,000 enslaved persons and their enslavers lived in Harris County before the Civil War.