Spoken language translation graphs re-decoding using automatic quality assessment

Laurent Besacier (1) , Benjamin Lecouteux (1) , Ngoc-Quang Luong (1) , Ngoc-Tien Le (1)

1 GETALP - Groupe d’Étude en Traduction Automatique/Traitement Automatisé des Langues et de la Parole

This paper investigates how automatic quality assessment of spoken language translation (SLT), also named confidence estimation (CE), can help re-decoding SLT output graphs and improve the overall speech translation performance. Our graph redecoding method can be seen as a second-pass of translation. For this, a robust word confidence estimator for SLT is required. We propose several estimators based on our estimation of transcription (ASR) quality, translation (MT) quality, or both (combined ASR+MT). Using these word confidence measures to re-decode the spoken language translation graph leads to a significant BLEU improvement (more than 2 points) compared to our SLT baseline, for a French-English SLT task. These results could be applied to interactive speech translation or computer-assisted translation of speeches and lectures.

Mots clés: Quality estimation; Search graph red-ecoding; Spoken Language Translation (SLT); Word confidence estimation (WCE)

Domaines: Informatique et langage [cs.CL]

Laurent Besacier, Benjamin Lecouteux, Ngoc-Quang Luong, Ngoc-Tien Le. Spoken language translation graphs re-decoding using automatic quality assessment. IEEE Workshop on Automatic Speech Recognition and Understanding (ASRU), Dec 2015, Scotsdale, AZ, United States. ⟨10.1109/ASRU.2015.7404804⟩. ⟨hal-01289158⟩