Do automated transcripts help non-native speakers catch up on missed conversation in audio conferences?
Ari Hautasaari, Naomi Yamashita · 2014
Previous work has suggested that speeded up playback of recorded audio works well for native speakers (NS) to catch up on conversation they missed in real-time audio conferences. However, this might not be the case for non-native speakers (NNS) who normally have lower listening ability in their second language. In this study, we explore whether automated speech recognition (ASR) technology can aid NNS when combined with speeded up audio playback. We conducted a laboratory experiment in which 18 NS and 18 NNS listened to a pre-recorded audio conference with three English native speakers, during which they were briefly interrupted and missed parts of the ongoing conversation. They then caught up to the conversation with speeded up audio only (1.6x) and speeded up audio with ASR transcripts. Although ASR transcripts did not improve their comprehension of the conversational content when catching up, transcripts allowed NNS to shift their focus between the two modalities depending on their ability to follow second language speech in different audio speeds. The findings inform future development of ASR tools to support multilingual group communication.