A Study on Natural Expressive Speech: Automatic Memorable Spoken Quote Detection
Abstract
This paper presents a study on natural expressive speech during public talks. Specifically, we focus on how people convey important messages that may be retained in the audience’s consciousness. Our study aims to answer several questions. Why are some public speeches memorable and inspirational for the audience, while others are not? Why are some memorable/inspirational spoken quotes more popular than others? Being able to evaluate why certain spoken words are memorable/inspirational is not a trivial matter, and most studies on memorable quote detection are only limited to textual data. In this study, we use both linguistic and acoustic features of public speeches in TED talks. The results reveal that based on those linguistic and acoustic features, we are able to distinguish memorable spoken quotes and non-memorable spoken quotes with 70.4 % accuracy. Furthermore, we also analyze the important factors that affect the memorableness and popularity of spoken quotes.
Keywords
Automatic quote detection Memorable spoken quote Popularity analysisNotes
Acknowledgements
Part of this work was supported by JSPS KAKENHI Grant Number 26870371.
References
- Akthar F, Hahne C (2012) Rapid Miner 5 Operator Reference. Rapid-I GmbH. http://rapidminer.com/wpcontent/uploads/2013/10/RapidMiner_OperatorReference_en.pdf
- Bandersky M, Smith, DA (2012) A dictionary of wisdom and wit: learning to extract quotable phrase. In: Proceedings of NAACHL-HLT, Montréal, Canada, pp 69–77Google Scholar
- Bird S (2006) NLTK: the natural language toolkit. In: Proceedings of COLING/ACL on interactive presentation sessions, Sydney, pp 69–72Google Scholar
- Cristianini N, Taylor JS (2000) An introduction to support vector machines and other Kernel-based learning methods. Cambridge University Press, CambridgeCrossRefMATHGoogle Scholar
- Danescu-Niculescu-Mizil C, Cheng J, Kleinberg J, Lee L (2012) You had me at hello: how phrasing affects memorability. In: Proceedings of ACL, Jeju Island, pp 892–901Google Scholar
- Dautenhahn K (2007) Socially intelligent robots: dimensions of human-robot interaction. Philos Trans R Soc B 362:679–704CrossRefGoogle Scholar
- Eyben F, Woeller M, Schuller B (2010) openSMILE—the Munich versatile and fast open-source audio feature extractor. In: Proceedings of multimedia (MM), pp 1459–1462Google Scholar
- Fu L (1994) Neural network in computer intelligence. McGraw-Hill International Edition/MIT-Press, New York/CambridgeGoogle Scholar
- Kolak O, Schilit BN (2008) Generating links by mining quotations. In: Proceedings of 9th ACM conference on hypertext and hypermedia, pp 117–126Google Scholar
- Koto F, Sakti S, Neubig G, Toda T, Adriani M, Nakamura S. (2014) Memorable spoken quote corpora of TED public speaking. In: Proceedings of the 17th oriental COCOSDA, Phuket, pp 140–143Google Scholar
- Miller DR, Kleber M, Kao CL, Kimball O, Colthurst T, Lowe SA, Gish H (2007) Rapid and accurate spoken term detection. In: Proceedings of INTERSPEECH, pp 314–317Google Scholar
- Lewis DD (1998) Naive Bayes at forty: the independence assumption in information retrieval. In: Proceedings of ECML-98, Berlin, Heidelberg, pp 4–15Google Scholar
- Liang J, Dhillon N, Koperski K (2010) A large-scale system for annotating and querying quotations in news feeds. In: Proceeding of 3rd international semantic search workshop, p 7Google Scholar
- Schuller B, Steidl S, Batliner A, Burkhardt F, Devillers L, Muller CA, Narayanan SS (2010) The INTERSPEECH 2010 paralinguistic challenge. In: Proceedings of INTERSPEECH, Makuhari, pp 2794–2797Google Scholar
- Vergyri D, Shafran I, Stolcke A, Gadde VRR, Akbacak M, Roark B, Wang W (2006) The SRI/OGI 2006 spoken term detection system. In: Proceedings of INTERSPEECH, pp 2393–2396Google Scholar