Disentangling ASR and MT Errors in Speech Translation

Ngoc-Tien Le (1, 2, 3) , Benjamin Lecouteux (1, 2, 3) , Laurent Besacier (4, 1, 2, 3)

1 LIG - Laboratoire d'Informatique de Grenoble
2 UGA [2016-2019] - Université Grenoble Alpes [2016-2019]
3 GETALP - Groupe d’Étude en Traduction Automatique/Traitement Automatisé des Langues et de la Parole
4 IUF - Institut universitaire de France

The main aim of this paper is to investigate automatic quality assessment for spoken language translation (SLT). More precisely, we investigate SLT errors that can be due to transcription (ASR) or to translation (MT) modules. This paper investigates automatic detection of SLT errors using a single classifier based on joint ASR and MT features. We evaluate both 2-class (good/bad) and 3-class (good/badASR/badMT) labeling tasks. The 3-class problem necessitates to disentangle ASR and MT errors in the speech translation output and we propose two label extraction methods for this non trivial step. This enables-as a by-product-qualitative analysis on the SLT errors and their origin (are they due to transcription or to translation step?) on our large in-house corpus for French-to-English speech translation.

Mots clés: Spoken Language Translation; Automatic Speech Recognition; Confidence Estimation; Quality Estimation; ASR and MT errors detection

Domaines: Informatique et langage [cs.CL]

Ngoc-Tien Le, Benjamin Lecouteux, Laurent Besacier. Disentangling ASR and MT Errors in Speech Translation. MT Summit 2017, Sep 2017, Nagoya, Japan. ⟨hal-01580877⟩