Chatbot Technology with Synthetic Voices in the Acquisition of an Endangered Language: Motivation, Development and Evaluation of a Platform for Irish

Chatbot Technology with Synthetic Voices in the Acquisition of an Endangered Language: Motivation, Development and Evaluation of a Platform for Irish Neasa Ní Chiaráin, Ailbhe Ní Chasaide Trinity College, Dublin E-mail: nichiarn@tcd.ie, anichsid@tcd.ie Abstract This paper describes the development and evaluation of a chatbot platform designed for the teaching/learning of Irish. The chatbot uses synthetic voices developed for the dialects of Irish. Speech-enabled chatbot technology offers a potentially powerful tool for dealing with the challenges of teaching/learning an endangered language where learners have limited access to native speaker models of the language and limited exposure to the language in a truly communicative setting. The sociolinguistic context that motivates the present development is explained. The evaluation of the chatbot was carried out in 13 schools by 228 pupils and consisted of two parts. Firstly, learners’ opinions of the overall chatbot platform as a learning environment were elicited. Secondly, learners evaluated the intelligibility, quality, and attractiveness of the synthetic voices used in this platform. Results were overwhelmingly positive to both the learning platform and the synthetic voices and indicate that the time may now be ripe for language learning applications which exploit speech and language technologies. It is further argued that these technologies have a particularly vital role to play in the maintenance of the endangered language. Keywords: Computer-Assisted Language Learning, TTS synthesis, Chatbot, Irish, Minority Languages 1. Introduction This paper describes the design, development and evaluation of a chatbot which can be used as a simple interactive dialogue system for the teaching of the Irish language (Gaeilge) in the realm of Computer-Assisted Language Learning (CALL). Chatbots are programs that can interact with humans using natural language. They come in a variety of forms, many having avatars with greater or lesser similarities to a human being. The chatbot presented here is part of the ABAIR speech technology initiative, School of Linguistic, Speech and Communication Studies, Trinity College, Dublin (TCD). ABAIR has developed synthetic voices for the three main Irish dialects (available to the public at www.abair.ie) and is exploring their exploitation for educational and disability applications. Chatbots are still a very new addition to CALL: there is little information available on their use and few evaluations of their effectiveness as a component of CALL (Georgila et al., 2012). Similarly, there has been little use to date of synthetic speech in CALL applications. The system developed here is thus in many ways quite exploratory, not only in the use of chatbots, but also in showcasing how synthetic speech can enhance the learning environment. In this paper, we describe the development and evaluation of a specific chatbot application with synthetic voices. The development of the synthetic voices has been described elsewhere (ABAIR, 2016; Ní Chasaide et al., 2015) and we focus specifically here on the chatbot and on how it exploits these voices. In terms of the evaluation that is carried out, there is a dual goal. Firstly, we set out to elicit learners’ opinions of the chatbot as a learning environment. Furthermore, we …

Content truncated to 500 words