Robert Chartrand is a Professor of English at the Institute of Foreign Language Education, Kurume University, in Fukuoka Prefecture. His main interests are in CALL research, Corpus Linguistics, and Artificial Intelligence uses for learning languages.
Recently, there are been a number of innovations in Speech Recognition (SR) to enhance the ability of technology-enabled devices to interact with human beings. We can, for example, conduct simple conversations and order some devices to carry out commands with digital assistants such as Apple’s Siri, Google Assistant and Amazon Alexa. The Human-Computer Interaction (HCI) is enhanced and the ability of a device to understand the spoken language has improved dramatically. Although the Voice User Interface (VUI) of computers and mobile devices to recognize English speech can very high, the ability to respond to such speech depends on a conversational corpus and Artificial Intelligence (AI) algorithms. Speakers can make use of such devices to transcribe speech to text, ask simple questions, and perform simple translations. Language learners can use such advanced methods for self-study and conversation practice. The problem lies in the ability of the foreign language learner to produce language that is native-like so that the device can understand the speech. Factors such as pronunciation, grammar mistakes, word order and use of proper vocabulary all contribute to the ability of the device to understand the spoken language. As the algorithms of these devices advance from a command-based structure to a more conversational one, there is a vast potential in using this technology to empower language learners. I will demonstrate some of the techniques that can be used for language practice with digital assistants and will encourage discussion on this new and relevant topic.