Error correction strategies of professional speech recognition users: Three profiles

Leijten, Mariëlle; Janssen, Daniël; Waes, Luuk Van

doi:10.1016/j.chb.2010.02.010

Cited by 21 publications

(13 citation statements)

References 16 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…To collect cognitive data during the writing process, many researchers have used “thinking aloud protocols” (TAPs), either concurrent or retrospective. Starting from the early work of Matsuhashi and Hayes (Hayes & Flower, 1980; Matsuhashi, 1982), TAPs have been used to address a variety of research objectives in writing research and related domains, including the relationship between online management and text quality in narrative and argumentative texts (Beauvais, Olive, & Passerault, 2011), the development of academic writing (Llosa, Beck, & Zhao, 2011), the influence of new media on writing (Leijten, Van Waes, & Janssen, 2010), and the comparison of first language and second language writing (e.g., Van Weijen, 2008). TAPs were developed in the field of cognitive psychology by Ericsson and Simon (1984, 1993).…”

Section: Combining Keystroke Logging With Other Research Methodsmentioning

confidence: 99%

Keystroke Logging in Writing Research

Leijten

Waes

2013

Written Communication

Self Cite

364

119

View full text Add to dashboard Cite

Keystroke logging has become instrumental in identifying writing strategies and understanding cognitive processes. Recent technological advances have refined logging efficiency and analytical outputs. While keystroke logging allows for ecological data collection, it is often difficult to connect the fine grain of logging data to the underlying cognitive processes. Multiple methodologies are useful to offset these difficulties. In this article we explore the complementarity of the keystroke logging program Inputlog with other observational techniques: thinking aloud protocols and eyetracking data. In addition, we illustrate new graphic and statistical data analysis techniques, mainly adapted from network analysis and data mining. Data extracts are drawn from a study of writing from multiple sources. In conclusion, we consider future developments for keystroke logging, in particular letter- to word-level aggregation and logging standardization.

show abstract

Section: Combining Keystroke Logging With Other Research Methodsmentioning

confidence: 99%

Keystroke Logging in Writing Research

Leijten

Waes

2013

Written Communication

Self Cite

364

119

View full text Add to dashboard Cite

show abstract

“…Writers may alternatively use dictation software, as discussed by Leijten, Janssen, and Van Waes (2010). For example, there are facilities that expand abbreviations or short forms into longer words and expressions by allowing writers to omit vowels, use only stems of words, or take advantage of the phonetic characteristics of a language, so that they might type homophones using the same characters.…”

Section: Supporting Specific Aspects Of the Writing Processmentioning

confidence: 99%

12 Production media: Writing as using tools in media convergent environments

Mahlow¹,

Dale²

2014

Handbook of Writing and Text Production

View full text Add to dashboard Cite

Writing requires a tool and a medium. Technology affords previously inconceivable ways of extending the functionalties of both. In this chapter, we focus on electronic writing tools, highlighting differences to older writing tools like pen and paper. We set the context by providing a brief history of word processing technology, before going on to survey the scope for tools that provide writing assistance to authors. We begin by surveying existing work on spell checking, grammar checking, and style checking, along with some specialist needs that can be met with existing tools. We then go on to look at the broader context of writing, exploring how state-ofthe-art natural language processing technologies might provide support for aspects of the writing process that, to date, have been out of reach for machines. We show the influence of input devices and word processor features on the writing process as well as on the resulting text. The chapter also covers aspects of fully automated text production, where writing is done by a machine. Writers and their toolsWriting is impossible without a tool and a medium: we write with a finger in the sand, with a pen on paper, with a spray can on a wall, or with a keyboard and intermediating software on a computer. Writers have to consider the topic and genre of what they are writing, take the audience into account, find the right words, and master their writing tool -all at the same time. Writing is also a task whose physical demands vary depending on the tools and media used: in former times, texts were produced on marble columns or clay tablets; using a typewriter from the 1980s is more exhausting than using a keyboard from the 21st century.The writer interacts with a tool and a medium to produce text. Given a class of writing tools -e.g., pen, typewriter, or keyboard and word processor -writers usually develop preferences. From the literature, we know about the writing habits of authors like Friedrich Nietzsche, Thomas Mann, Gabriel García Márquez, and Neal Stephenson, who relied on the use of a certain type of nib, typewriter, or word processor. The medium is also important: authors using a pen, a nib, or a typewriter not only prefer a certain type of the tool (including elements such as a specific ink or typewriter ribbon), but also a very specific type of paper. Others using word processors prefer certain types of screens or input devices. Authors may need a specific environment to produce text: Brought to you by |

show abstract

“…As stated by Leijten and Van Waes (2005, 741), "most research in the field of speech technology has dealt with the technical improvement of speech recognition and the role of phonology". However, more recently there has been interesting work on the applications of speech recognition in a range of other fields, for example, studies on how SR affects the writing process (Leijten and Van Waes 2005), on error correction strategies employed by professional SR users (Leijten, Janssen and Van Waes 2010), and on the use of SR technology in the domain of re-speaking in live subtitling (Luyckx et al 2010). However, to our knowledge there are no studies such as the one below on the use of SR in translator training.…”

Section: Scenariomentioning

confidence: 99%