The automatic analysis of classroom talk
Kronholm, H., Caballero, D., Mansikkaniemi, A., Araya, R., Lehesvuori, S., Pertilä, P., Virtanen, T., Kurimo, M., & Viiri, J. (2017). The automatic analysis of classroom talk. In Proceedings of the annual FMSERA symposium 2016 (pp. 142-151). Finnish Mathematics and Science Education Research Association (FMSERA). Proceedings of the FMSERA annual symposium. https://journal.fi/fmsera/article/view/60940/27049
Published in
Proceedings of the FMSERA annual symposiumDate
2017Copyright
© the Authors, 2017. This is an open access article distributed under the terms of a Creative Commons License.
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.
Publisher
Finnish Mathematics and Science Education Research Association (FMSERA)Conference
Finnish Mathematics and Science Education Research Association annual symposiumIs part of publication
Proceedings of the annual FMSERA symposium 2016ISSN Search the Publication Forum
2489-4583Keywords
Original source
https://journal.fi/fmsera/article/view/60940/27049Publication in research information system
https://converis.jyu.fi/converis/portal/detail/Publication/27344762
Metadata
Show full item recordCollections
License
Except where otherwise noted, this item's license is described as © the Authors, 2017. This is an open access article distributed under the terms of a Creative Commons License.