Automatic speech recognition: Reliability and pedagogical implications for teaching pronunciation

This study examines the reliability of automatic speech recognition (ASR) software used to teach English pronunciation, focusing on one particular piece of software, FluSpeak, as a typical example. Thirty-six Korean English as a Foreign Language (EFL) college students participated in an experiment in which they listened to 15 sentences that appeared in FluSpeak and recorded their voices, repeating sentence by sentence. The ASR software analysis of their production was then compared to pronunciation scores determined by native English speaking (NES) instructors. Although the correlation coefficient for intonation was nearly zero, indicating that ASR technology is still not as accurate as human analysis, the software may be very useful for student practice with aspects of pronunciation. The paper suggests a lesson plan for teaching English pronunciation through ASR software.