Synthetic speech in foreign language learning: an evaluation by learners

Abstract

Can synthetic speech be utilized in foreign language learning as natural speech? In this paper, we evaluated synthetic speech from the viewpoint of learners in order to find out an answer. The results pointed out that learners do not recognize remarkable differences between synthetic voices and natural voices for the words with short vowels and long vowels when they try to understand the meanings of the sounds. The data explicates that synthetic voice utterances of sentences are easier to understand and more acceptable by learners compared to synthetic voice utterances of words. In addition, the ratings on both synthetic voices and natural voices strongly depend upon the learners' listening comprehension abilities. We conclude that some synthetic speech with specific pronunciations of vowels may be suitable for listening materials and suggest that evaluating TTS systems by comparing synthetic speech with natural speech and building a lexical database of synthetic speech that closely approximates natural speech will be helpful for teachers to readily use many existing CALL tools.

An evaluation of TTS as a pedagogical tool for pronunciation instruction: the ‘foreign’ language context

“…The findings correspond to previous studies (e.g. Cardoso et al, 2015) and to those obtained in Kang, Kashiwagi, Treviranus, and Kaburagi (2008), who found that non-native English learners do not recognise a significant difference between synthetic and human voices. Contrary to previous studies, such as Bailly (2003), this study found that artificial and human speech were equally intelligible and comprehensible.…”

Proceedings of the Workshop on NLG for Human–Robot Interaction

“…In the context of language acquisition, the quality of the synthesised speech may be of importance, as (young) learners have been shown to attend to non-verbal cues present in the speech signal when presented with a novel language (e.g., Dominey and Dodane, 2004). Although the effects of speech synthesis quality on learners' perceptions have previously been studied for computerassisted language learning (e.g., Bione et al, 2016;Handley, 2009;Kang et al, 2008), whether poor quality speech synthesis impedes the efficacy of language acquisition has not been unequivocally established.…”

Effects of Educational Context on Learners’ Ratings of a Synthetic Voice

“…To date, text-to-speech (TTS) synthesis has not been used very frequently as an integral part of Computer-Assisted Language Learning (CALL) systems [5]- [7]. In earlier years this was largely because of the relatively poor quality of the synthetic voices and their inability to closely imitate the human voice [8].…”

“…It has also been suggested that a learner's evaluation may be quite different to that of a native speaker. Kang et al [7] found that learners' general listening comprehension abilities influenced their ratings of synthetic voices. Stern et al [27] suggested that synthetic voices are judged more positively when they are presented as emanating from a computer rather than being human voices.…”