REPORT Dubagunta_Idiap-RR-11-2021/IDIAP Towards Automatic Prediction of Non-Expert Perceived Speech Fluency Ratings Dubagunta, S. Pavankumar Moneta, Edoardo Theocharopoulos, Eleni Magimai-Doss, Mathew articulatory features bag of audio words low level descriptors Perceived fluency raw waveform modelling speech assessment Zero frequency filtering EXTERNAL http://publications.idiap.ch/attachments/reports/2021/Dubagunta_Idiap-RR-11-2021.pdf PUBLIC Idiap-RR-11-2021 2021 Idiap August 2021 Automatic speech fluency prediction has been mainly approached from the perspective of computer aided language learning, where the system tends to predict ratings similar to those of the human experts. Speech fluency prediction, however, can be questioned in a more relaxed social setting, where the ratings arise mostly from non-experts. This paper explores the latter direction, i.e., prediction of non-expert perceived speech fluency ratings, which has not been studied in the speech technology literature, to the best of our knowledge. Toward that, we investigate different approaches, namely, (a) low-level descriptor feature functionals, (b) bag-of-audio word based approach and (c) neural network based end-to-end acoustic modelling approach. Our investigations on speech data collected from 54 speakers and rated by seven non-experts demonstrate that non-expert speech fluency ratings can be systematically predicted, with the best performing system yielding a Pearson's correlation coefficient of 0.66 and a Spearman's correlation coefficient of 0.67 with the median human scores.