Patterns of entry and correction in large vocabulary continuous speech recognition systems
Proceedings of the SIGCHI conference on Human Factors in Computing Systems
Computer Speech Technology
Accuracy improvement for a voice recognition using field association knowledge
International Journal of Computer Applications in Technology
Error correction strategies of professional speech recognition users: Three profiles
Computers in Human Behavior
Third-party error detection support mechanisms for dictation speech recognition
Interacting with Computers
Online writing data representation: a graph theory approach
IDA'11 Proceedings of the 10th international conference on Advances in intelligent data analysis X
Hi-index | 0.00 |
This paper describes the adaptation and writing process of writers who have started using speech recognition systems for writing business texts. The writers differ in their previous writing experience. They either have previous classical dictating experience or they are used to writing their texts with a word processor. To gather the process data for this study we chose complementary research methods. First the participants were asked to fill in a questionnaire and given instruction about the speech recognition system. Then they were observed five times using the speech recognition system during their day-to-day work. Finally, they also filled in a logging questionnaire after each task. The quantitative analysis of the use of the writing mode shows that those participants who had no previous dictating experience, tend to use the voice input more extensively, both for formulating and reviewing. This result is confirmed in the more detailed case analysis. The other analyses in the case study-i.e. repair, revision, and pause analysis-refine the differences in the organization of the writing process between the writers, and show that the speech recognition mode seems to create a writing environment that is open for different writing profiles.