Speaking your Translation: Students' First Encounter with Speech Recognition Technology

Barbara Dragsted; Inger M. Mees; Inge Gorm Hansen

Speaking your Translation: Students' First Encounter with Speech Recognition Technology

Barbara Dragsted, Inger M. Mees, Inge Gorm Hansen

Research output: Contribution to journal › Journal article › Research › peer-review

Abstract

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.

Original language	English
Journal	Translation & Interpreting
Volume	3
Issue number	1
Pages (from-to)	10-43
ISSN	1836-9324
Publication status	Published - 2011

Keywords

Translation Processes
Oral and Written Translation
Sight Translation
Speech Recognition Software
Translation Quality
Pronunciation

Access to Document

Handle.net

Persistent link

Cite this

@article{9d9516ce17754752b6110f687220695d,

title = "Speaking your Translation: Students' First Encounter with Speech Recognition Technology",

abstract = "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. ",

keywords = "Translation Processes, Oral and Written Translation, Sight Translation, Speech Recognition Software, Translation Quality, Pronunciation",

author = "Barbara Dragsted and Mees, {Inger M.} and {Gorm Hansen}, Inge",

year = "2011",

language = "English",

volume = "3",

pages = "10--43",

journal = "Translation & Interpreting",

issn = "1836-9324",

publisher = "University of Western Sydney. Interpreting & Translation Research Group",

number = "1",

}

TY - JOUR

T1 - Speaking your Translation

T2 - Students' First Encounter with Speech Recognition Technology

AU - Dragsted, Barbara

AU - Mees, Inger M.

AU - Gorm Hansen, Inge

PY - 2011

Y1 - 2011

N2 - 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.

AB - 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.

KW - Translation Processes

KW - Oral and Written Translation

KW - Sight Translation

KW - Speech Recognition Software

KW - Translation Quality

KW - Pronunciation

M3 - Journal article

SN - 1836-9324

VL - 3

SP - 10

EP - 43

JO - Translation & Interpreting

JF - Translation & Interpreting

IS - 1

ER -