Speaking of accent: A content analysis of accent misconceptions in ASR research

Abstract

Automatic speech recognition (ASR) researchers are working to address the differing transcription performance of ASR by accent or dialect. However, research often has a limited view of accent in ways that reproduce discrimination and limit the scope of potential solutions. In this paper we present a content analysis of 22 papers published in 2022 in top conferences and journals on the topic of accent and ASR. We report on how accent is sometimes mistakenly viewed as something some people don't have; as having a default; and being an attribute only of the speaker, and not of the listener. We discuss the implications on research and provide recommendations to researchers who hope to reduce ASR biases by accent.