Writing with automatic speech recognition: Examining user’s behaviours and text quality (lexical diversity)

Abstract

This study explores the potential of Automatic Speech Recognition (ASR) as a writing tool by investigating user behaviours (strategies henceforth) and text quality (lexical diversity) when users engage with the technology. Thirty English second language writers dictated texts into an ASR system (Google Voice Typing) while also using optional additional input devices, such as keyboards and mice. Analysis of video recordings and field observations revealed four strategies employed by users to produce texts: use of ASR exclusively, ASR in tandem with keyboarding, ASR followed by keyboarding, and ASR followed by both keyboarding and ASR. These strategies reflected cognitive differences and text generation challenges. Text quality was operationalized through lexical diversity metrics. Results showed that ASR use in tandem with keyboarding and ASR followed by both keyboarding and ASR yielded greater lexical diversity, whereas the use of ASR exclusively or ASR followed by keyboarding had lower diversity. Findings suggest that the integrated use of ASR and keyboarding activates dual channels, thus dispersing cognitive load and possibly improving text quality (i.e. lexical diversity). This exploratory study demonstrates potential for ASR as a complementary writing tool and lays groundwork for further research on the strategic integration of ASR and keyboarding to improve the quality of written texts.