Automatic speech recognition in the booth
Assessment of system performance, interpreters’ performances and interactions in the context of numbers
Bart Defrancq | Ghent University
Claudio Fantinuoli | Johannes Gutenberg University Mainz
Automatic Speech Recognition (ASR) has been proposed as a means to enhance state-of-the-art computer-assisted interpreting
(CAI) tools and to allow machine-learning techniques to enter the workflow of professional interpreters. In this article, we test the
usefulness of real-time transcription with number highlighting of a source speech for simultaneous interpreting using InterpretBank ASR. The
system’s precision is high (96%) and its latency low enough to fit interpreters’ ear–voice span (EVS). We evaluate the potential benefits
among first-time users of this technology by applying an error matrix and by investigating the users’ subjective perceptions through a
questionnaire. The results show that the ASR provision improves overall performance for almost all number types. Interaction with the ASR
support is varied and participants consult it for just over half of the stimuli. The study also provides some evidence of the psychological
benefits of ASR availability and of overreliance on ASR support.
Keywords: automatic speech recognition, simultaneous interpreting, rendition of numbers, computer-assisted interpreting
Article outline
- 1.Introduction
- 2.Interpreting numbers
- 3.Methodology
- 3.1InterpretBank
- 3.2Preliminary test
- 3.3Equipment
- 3.4Participants
- 3.5Speeches
- 3.6Procedure
- 3.7Data processing and analysis
- 4.Results
- 4.1Findings regarding ASR
- 4.1.1Ergonomics
- 4.1.2Latency
- 4.1.3ASR precision for numbers
- 4.2Findings regarding presumed use of the ASR
- 4.3Findings regarding performance
- 4.3.1Renditions, ASR availability and presumed use
- 4.3.2Results per interpreter
- 4.3.3Renditions and number type
- 4.1Findings regarding ASR
- 5.Discussion
- 6.Conclusions
- Acknowledgements
- Notes
-
References
Published online: 26 November 2020
https://doi.org/10.1075/target.19166.def
https://doi.org/10.1075/target.19166.def
References
Alessandrini, Maria Serena
Braun, Susanne, and Andrea Clarici
Brüsewitz, Nora
2019 “Simultandolmetschen 4.0: Ist automatische Spracherkennung der nächste Schritt? [Simultaneous interpreting 4.0: Is automatic speech recognition the next step?]” In Proceedings of Übersetzen und Dolmetschen 4.0. – Neue Wege im digitalen Zeitalter [Translation and Interpreting 4.0 – New Paths in the Digital Era], edited by Wolfram Bauer and Felix Mayer, 323–333. Berlin: BDÜ Fachverlag.
Christoffels, Ingrid K.
Collard, Camille
Corpas Pastor, Gloria, and Lily May Fern
Defrancq, Bart
Desmet, Bart, Mieke Vandierendonck, and Bart Defrancq
Fantinuoli, Claudio
Frittella, Francesca Maria
Gile, Daniel
Korpal, Paweł
Korpal, Paweł, and Katarzyna Stachowiak-Szymczak
Lamberger-Felber, Heike
Mazza, Cristina
Mead, Peter
Oléron, Pierre, and Hubert Nanpon
Pinochi, Diletta
Prandi, Bianca
Setton, Robin, and Andrew Dawrant
Vogler, Nicolai, Craig Stewart, and Graham Neubig
2019 “Lost in Interpretation: Predicting Untranslated Terminology in Simultaneous Interpretation.” ArXiv:1904.00930 [Cs]. http://arxiv.org/abs/1904.00930