Gonzalo Luzardo
Katherine Chiluiza
Xavier Ochoa
ABSTRACT
This paper proposes a simple estimation of the quality of student oral presentations. It is based on the study and analysis of features extracted from the audio and digital slides of 448 presentations. The main goal of this work is to automatically predict the values assigned by professors to different criteria in a presentation evaluation rubric. Machine Learning methods were used to create several models that classify students in two clusters: high and low performers. The models created from slide features were accurate up to 65%. The most relevant features for the slide-base models were: number of words, images, and tables, and the maximum font size. The audio-based models reached up to 69% of accuracy, with pitch and filled pauses related features being the most significant. The relatively high degrees of accuracy obtained with these very simple features encourage the development of automatic estimation tools for improving presentation skills.
- D. Aha and D. Kibler. Instance-based learning algorithms. Machine Learning, 6:37--66, 1991. Google Scholar
Digital Library
- G. An, D.-G. Brizan, and A. Rosenberg. Detecting laughter and filled pauses using syllable-based features. In INTERSPEECH, pages 178--181, 2013.Google Scholar
- K. Audhkhasi, K. Kandhway, O. D. Deshmukh, and A. Verma. Formant-based technique for automatic filled-pause detection in spontaneous spoken english. In Acoustics, Speech and Signal Processing, 2009. ICASSP 2009. IEEE International Conference on, pages 4857--4860. IEEE, 2009. Google ScholarDigital Library
- J. Benkí, J. Broome, F. Conrad, R. Groves, and F. Kreuter. Effects of speech rate, pitch, and pausing on survey participation decisions. In Proc. Surv. Res. Meth. Sect. Am. Statist. Ass, 2011.Google Scholar
- E. Bhattacharyya and H. Bt Idrus. To speak like an engineer: Communicative competence in technical oral presentations through the lens of students and industry practitioners. In Teaching, Assessment and Learning for Engineering (TALE), 2013 IEEE International Conference on, pages 796--799, Aug 2013.Google ScholarCross Ref
- J. Bourhis and M. Allen. The role of videotaped feedback in the instruction of public speaking: A quantitative synthesis of published empirical research. Communication Research Reports, 15(3):256--261, 1998.Google ScholarCross Ref
- L. Breiman. Random forests. Machine learning, 45(1):5--32, 2001. Google ScholarDigital Library
- E. Bulska. Good oral presentation of scientific work. Analytical and bioanalytical chemistry, 385(3):403--405, 2006.Google Scholar
- M. Carter. 15. The use of slides in oral presentations. In Designing Science Presentations, pages 191--201. Academic Press, San Diego, 2013.Google ScholarCross Ref
- M. Cavanagh, M. Bower, R. Moloney, and N. Sweller. The effect over time of a video-based reflection system on preservice teachers' oral presentations. Australian Journal of Teacher Education, 39(6):1, 2014.Google ScholarCross Ref
- J. G. Cleary and L. E. Trigg. K*: An instance-based learner using an entropic distance measure. In 12th International Conference on Machine Learning, pages 108--114, 1995.Google ScholarDigital Library
- W. W. Cohen. Fast effective rule induction. In Twelfth International Conference on Machine Learning, pages 115--123. Morgan Kaufmann, 1995.Google ScholarDigital Library
- M. Cooper. Presentation video retrieval using automatically recovered slide and spoken text, 2013.Google Scholar
- N. Cristianini and J. Shawe-Taylor. An introduction to support vector machines and other kernel-based learning methods. Cambridge university press, 2000. Google ScholarDigital Library
- N. de Jong and T. Wempe. Praat script to detect syllable nuclei and measure speech rate automatically. Behavior Research Methods, 41(2):385--390, 2009.Google ScholarCross Ref
- N. Erdemir. The effect of powerpoint and traditional lectures on students' achievement in physics. Journal of Turkish Science Education (TUSED), 10(3):176, 2011.Google Scholar
- K. Gorovoy, J. Tung, and P. Poupart. Automatic speech feature extraction for cognitive load classification. In Conference of the Canadian Medical and Biological Engineering Society (CMBEC), 2010.Google Scholar
- L. D. Grez, M. Valcke, and I. Roozen. The impact of an innovative instructional intervention on the acquisition of oral presentation skills in higher education. Computers & Education, 53(1):112--120, 2009. Google ScholarDigital Library
- R. Hincks. Processing the prosody of oral presentations. In InSTIL/ICALL Symposium 2004, 2004.Google Scholar
- Y. Hu and X. Wan. Ppsgen: learning to generate presentation slides for academic papers. In Proceedings of the Twenty-Third international joint conference on Artificial Intelligence, pages 2099--2105. AAAI Press, 2013. Google ScholarDigital Library
- M. Jamie. Scoring power points. The Educational Technology Journal, 10(1), September 2000.Google Scholar
- K. K. Jensen and V. Harris. The public speaking portfolio. Communication Education, 48(3):211--227, 1999.Google ScholarCross Ref
- A. Khellaf, A. Beghdadi, and H. Dupoisot. Entropic contrast enhancement. Medical Imaging, IEEE Transactions on, 10(4):589--592, 1991.Google Scholar
- F. J. Koopmans-van Beinum and M. E. van Donzel. Discourse structure and its influence on local speech rate. In Proceedings of the Institute of Phonetic Sciences, volume 20, pages 1--11, 1996.Google Scholar
- S. le Cessie and J. van Houwelingen. Ridge estimators in logistic regression. Applied Statistics, 41(1):191--201, 1992.Google ScholarCross Ref
- D. Magin and P. Helmore. Peer and teacher assessments of oral presentation skills: how reliable are they? Studies in Higher Education, 26(3):287--298, 2001.Google ScholarCross Ref
- Y. Ming, Q. Ruan, and X. Li. Automatic assessment of oral mandarin proficiency based on speech recognition and evaluation. In Educational and Information Technology (ICEIT), 2010 International Conference on, volume 3, pages V3--37. IEEE, 2010.Google ScholarCross Ref
- G. Mohammadi and A. Vinciarelli. Humans as feature extractors: Combining prosody and personality perception for improved speaking style recognition. In Systems, Man, and Cybernetics (SMC), 2011 IEEE International Conference on, pages 363--366, 2011.Google Scholar
- J. R. Quinlan. C4. 5: programs for machine learning, volume 1. Morgan kaufmann, 1993. Google ScholarDigital Library
- V. N. Shaw. Reading, presentation, and writing skills in content courses. College Teaching, 47(4):153--157, 1999.Google ScholarCross Ref
- D. Talkin. A robust algorithm for pitch tracking (rapt). Speech coding and synthesis, 495:518, 1995.Google Scholar
Index Terms
- Estimation of Presentations Skills Based on Slides and Audio Features
Recommendations
Combination of audio and lyrics features for genre classification in digital audio collections
MM '08: Proceedings of the 16th ACM international conference on MultimediaIn many areas multimedia technology has made its way into mainstream. In the case of digital audio this is manifested in numerous online music stores having turned into profitable businesses. The widespread user adaption of digital audio both on home ...
Improving mood classification in music digital libraries by combining lyrics and audio
JCDL '10: Proceedings of the 10th annual joint conference on Digital librariesMood is an emerging metadata type and access point in music digital libraries (MDL) and online music repositories. In this study, we present a comprehensive investigation of the usefulness of lyrics in music mood classification by evaluating and ...
Discriminating Between Pitched Sources in Music Audio
Though humans find it relatively easy to identify and/or isolate different sources within polyphonic music, the emulation of this ability by a computer is a challenging task, and one that has direct relevance to music content description and information ...
Comments