What? I Didn’t Say THAT!: Linguistic strategies when speaking to write

Abstract

This study attempts to identify strategies peculiar to speakers of non-standard varieties of American English when composing with speech recognition-based dictation software. Two speakers of African American Vernacular English and one non-native speaker of English were asked to orally compose a series of college-level writing tasks using ViaVoice 98. The findings indicate that when the software misrecognized their speech, the language minority students resorted to similar strategies as those of standard American speakers discussed in the literature such as speaker adaptation to recognition systems leading to hyperarticulation and other types of phonetic and lexical adjustments. Moreover, the participants based their strategies on their knowledge of human-to-human interaction (e.g., the sequential organization of talk), which more often than not proved to be useless when interacting with the software. Yet, the students did seem to build up an awareness during the speech sessions of their linguistic variety and its divergence from the standard American accent that the software was originally modeled after. The findings of this study offer a better understanding of some of the strategies that speakers from diverse ethno-linguistic backgrounds may employ when speaking to write with speech recognition-based dictation software. They also offer some insight into users’ assumptions about the capabilities of the system, i.e., what they believed the speech-based software could process in terms of utterance length, tone of voice, canonical pronunciation, and lexical items.