The automatic analysis of classroom talk

Abstract

The SMART SPEECH Project is a joint venture between three Finnish universities and a Chilean university. The aim is to develop a mobile application that can be used to record classroom talk and enable observations to be made of classroom interactions. We recorded Finnish and Chilean physics teachers’ speech using both a conventional microphone/dictator setup and a microphone/mobile application setup. The recordings were analysed via automatic speech recognition (ASR). The average word error rate achieved for the Finnish teachers’ speech was under 40%. The ASR approach also enabled us to determine the key topics discussed within the Finnish physics lessons under scrutiny. The results here were promising as the recognition accuracy rate was about 85% on average.