Abstract
We are developing a conversation support system that provides an interesting new topic to a speaker taking part in a conversation with suitable timing by considering the degree of smoothness of the conversation. To provide a suitable topic, it is better that the system understand the speaker’s profile and what topics they frequently talk about. We have already confirmed that the topic and its depth depend on the generation of the speaker, and that the words suggested should be changed appropriately according to the age of the speaker. To estimate the speaker’s generation using the acoustic and linguistic characteristics of the conversation, we focused on the end of patterns of each utterance in the conversation and analyzed the standard deviation values of the fundamental frequency (F0) and speech power level (SPL) and the number of function words. We calculated these values for the utterances of the older and younger generations, and compared them. We confirmed that there is a tendency that the standard deviation of F0 and SPL values for the older generation are bigger than those of the younger generation, and the number of function words in the older generation’s utterances is larger than that in the younger generation’s utterances. The accuracy of our generation identification experiment is about 90%. We confirmed that these values can be effective in correctly categorizing a speaker's generation as young or old, based on their utterances.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Similar content being viewed by others
References
Kim, T., Chang, A., Holland, L., Pentland, A.S.: Meeting mediator: enhancing group collaboration using sociometric feedback. In: Proceedings of the 2008 ACM Conference on Computer Supported Cooperative Work, pp. 457–466 (2008)
Otsuka, K., Itoh, J., Munnemori, J.: Communication support system for enabling group management of community units. Procedia Comput. Sci. 60(1), 900–907 (2015)
Wakita, Y., Yoshida, Y., Nakamura, M.: Influence of personal characteristics on nonverbal information for estimating communication smoothness. In: Kurosu, M. (ed.) HCI 2016. LNCS, vol. 9733, pp. 148–157. Springer, Cham (2016). https://doi.org/10.1007/978-3-319-39513-5_14
Natsumi K, Wakita Y, Nakatoh Y, Effectiveness of dynamic image features for estimating daily conversation atmosphere Reviewed. In: IICAIET 2020 (2020)
Iida, Y., Wakita, Y.: Topic-shift characteristics of Japanese casual conversations between elderlies and between youths. In: The 24th International Conference HCI International 2020, July 2021
Skoog Waller, S., Eriksson, M., Sörqvist, P.: Can you hear my age? Influences of speech rate and speech spontaneity on estimation of speaker age. Front. Psychol. 6, 978. https://doi.org/10.3389/fpsyg.2015.00978. Published online (17 July 2015)
Martínez-Nicolás, I., Llorente, T.E, Ivanova, O., Martínez-Sánchez, F., Meilán, J.J.: Many changes in speech through aging are actually a consequence of cognitive changes. Int. J. Environ. Res. Publ. Health. 19(4):2137. Published online (14 Feb. 2022)
Nguyen, D., Gravel, R., Trieschnigg, D., Meder, T.: How old do you think i am?; A study of language and age in twitter. In: Proceedings of the Seventh International AAAI Conference on Weblogs and Social Media, vol. 7, no. 1 (2013)
Ariizumi, Y.: Effects of gender-differentiated sentence endings on impressions of the speaker. Jpn. Assoc. Socioling. Sci. 9(2), 3–12 (2007)
Ptaszynski, M., Dybala, P., Shi, W., Rzepka, R., Araki, K.: A system for affect analysis of utterances in Japanese supported with web mining. J. Jpn. Soc. Fuzzy Theory Intell. Inf. 21(2), 194–213 (2009)
Chang, C.-C., Lin, C.-J.: LIBSVM -- A Library for Support Vector Machines (2019). https://www.csie.ntu.edu.tw/~cjlin/libsvm/. Aaccessed 01 July 2020
Acknowledgment
This work is supported by JSPS KAKENHI Grant Number 19K04934.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2023 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this paper
Cite this paper
Nishida, H., Iida, Y., Wakita, Y. (2023). Age Estimation Function Using End-of Sentence Expression for Conversation Support System Based on Associative Words Board. In: Omatu, S., Mehmood, R., Sitek, P., Cicerone, S., Rodríguez, S. (eds) Distributed Computing and Artificial Intelligence, 19th International Conference. DCAI 2022. Lecture Notes in Networks and Systems, vol 583. Springer, Cham. https://doi.org/10.1007/978-3-031-20859-1_24
Download citation
DOI: https://doi.org/10.1007/978-3-031-20859-1_24
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-20858-4
Online ISBN: 978-3-031-20859-1
eBook Packages: Intelligent Technologies and RoboticsIntelligent Technologies and Robotics (R0)