Automatic Quality Assessment for Speech Translation Using Joint ASR and MT Features

TL;DR

This paper introduces a novel approach for automatic quality assessment of speech translation by combining features from automatic speech recognition and machine translation, utilizing a new corpus and sequence labeling.

Contribution

It proposes joint ASR and MT feature-based word confidence estimators for speech translation quality assessment, a new formalization and corpus for the task.

Findings

MT features are most influential for quality estimation

ASR features provide complementary information

Robust estimators can improve speech translation feedback

Abstract

This paper addresses automatic quality assessment of spoken language translation (SLT). This relatively new task is defined and formalized as a sequence labeling problem where each word in the SLT hypothesis is tagged as good or bad according to a large feature set. We propose several word confidence estimators (WCE) based on our automatic evaluation of transcription (ASR) quality, translation (MT) quality, or both (combined ASR+MT). This research work is possible because we built a specific corpus which contains 6.7k utterances for which a quintuplet containing: ASR output, verbatim transcript, text translation, speech translation and post-edition of translation is built. The conclusion of our multiple experiments using joint ASR and MT features for WCE is that MT features remain the most influent while ASR feature can bring interesting complementary information. Our robust quality estimators for SLT can be used for re-scoring speech translation graphs or for providing feedback to the user in interactive speech translation or computer-assisted speech-to-text scenarios.