Students' First Encounter with Speech Recognition Technology
In this article we discuss the translation processes and products of 14 MA students who produced translations from Danish (L1) into English (L2) under different working conditions: (1) written translation, (2) sight translation, and (3) sight translation with a speech recognition (SR) tool. Audio output and keystrokes were recorded. Oral and written translation data were examined in order to investigate if task times and translation quality differed in the three modalities. Although task times were found to be highest in written translation, the quality was not consistently better. In addition, since students were dictating in their L2, we looked into the number and types of error that occurred when using the SR software. Items that were misrecognised by the program could be divided into three categories: homophones, hesitations, and incorrectly pronounced words. Well over fifty per cent of the errors were caused by students‟ mispronunciations.
Translation and Interpreting, 2011, Vol 3, Issue 1, p. 10-43
Translation Processes; Oral and Written Translation; Sight Translation; Speech Recognition Software; Translation Quality; Pronunciation