%Aigaion2 BibTeX export from Idiap Publications
%Monday 29 April 2024 09:12:35 PM

@TECHREPORT{Dubagunta_Idiap-RR-11-2021,
         author = {Dubagunta, S. Pavankumar and Moneta, Edoardo and Theocharopoulos, Eleni and Magimai.-Doss, Mathew},
       keywords = {articulatory features, bag of audio words, low level descriptors, Perceived fluency, raw waveform modelling, speech assessment, Zero frequency filtering},
       projects = {Idiap},
          month = {8},
          title = {Towards Automatic Prediction of Non-Expert Perceived Speech Fluency Ratings},
           type = {Idiap-RR},
         number = {Idiap-RR-11-2021},
           year = {2021},
    institution = {Idiap},
       abstract = {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.},
            pdf = {https://publications.idiap.ch/attachments/reports/2021/Dubagunta_Idiap-RR-11-2021.pdf}
}