Interlanguage speech recognition by computer

Implications for SLA and computational machines

Abstract

During the last decade, there has been a rapid growth in research into speechrecognition by computer (SRC). Computerised voice recognition systems have beendeveloped which are being used for a variety of applications. However there remain awhole range of issues which have to be elucidated and investigated before SRC canbe broadly useful including for language learning purposes. It is well documentedthat speaker variability caused by accent is one of these issues and one of the majorhurdles in accurate speech recognition. Foreign speaker recognition is particularlyproblematic to program for reasons that our work is beginning to suggest. In thispaper we describe and compare the SRC of an interlanguage speaker ofItalian/English versus a native speaker of English, both with repetitive straindisorder (RSD) and thus highly motivated, using the same software, DragonDictate,from Dragon Systems. Cognitive processes such as language transfer, fossilizationand communication strategies are examined in light of the research. We illustratethe possibility of using SRC in second language research with particular emphasison phonology. In this paper we not only explain our views of the potentials of thisnew technology in facilitating second language acquisition research but go to a moregeneral applied linguistics issue where we briefly discuss some implications for thedesign of speech recognition systems for interlanguage speakers. This focus, webelieve, can help make applied linguistics a main stream discipline, therebyincreasing the job space for applied linguistics graduates.