KIT | KIT-Bibliothek | Impressum | Datenschutz

Augmenting Translation Models with Simulated Acoustic Confusions for improved Spoken Language Translation

Tsetkov, Yulia; Metze, Florian; Dyer, Chris

Abstract:

We propose a novel technique for adapting text-based statistical machine translation to deal with input from automatic speech recognition in spoken language translation tasks. We simulate likely misrecognition errors using only a source language pronunciation dictionary and language model (i.e., without an acoustic model), and use these to augment the phrase table of a standard MT system. The augmented system can thus recover from recognition errors during decoding using synthesized phrases. Using the outputs of five different English ASR systems as input, we find consistent and significant improvements in translation quality. Our proposed technique can also be used in conjunction with lattices as ASR output, leading to further improvements.

Zugehörige Institution(en) am KIT Institut für Anthropomatik und Robotik (IAR)
Publikationstyp Proceedingsbeitrag
Publikationsjahr 2014
Sprache Englisch
Identifikator ISBN: 978-1-937284-78-7
KITopen-ID: 1000166308
Erschienen in Proceedings of the 14th Conference of the European Chapter of the Association for Computational Linguistics. Ed.: S. Wintner, S. Goldwater, S. Riezler
Veranstaltung 14th Conference of the European Chapter of the Association for Computational Linguistics (EACL 2014), Göteborg, Schweden, 26.04.2014 – 30.04.2014
Verlag Association for Computational Linguistics (ACL)
Seiten 616–625
Nachgewiesen in OpenAlex
Dimensions
Scopus
Globale Ziele für nachhaltige Entwicklung Ziel 4 – Hochwertige Bildung

Verlagsausgabe §
DOI: 10.5445/IR/1000166308
Veröffentlicht am 23.01.2024
Originalveröffentlichung
DOI: 10.3115/v1/E14-1065
Scopus
Zitationen: 20
Dimensions
Zitationen: 14
Seitenaufrufe: 39
seit 23.01.2024
Downloads: 38
seit 01.02.2024
Cover der Publikation
KIT – Die Forschungsuniversität in der Helmholtz-Gemeinschaft
KITopen Landing Page