Enhancing End-to-End Conversational Speech Translation Through Target Language Context Utilization
This work addresses the challenge of maintaining coherence and resolving ambiguities in conversational speech translation for applications like real-time communication, though it is incremental as it builds on existing context utilization methods in machine translation.
The paper tackled the problem of improving end-to-end conversational speech translation by incorporating target language context, which enhanced coherence and overcame memory constraints, resulting in performance gains over isolated utterance-based approaches.
Incorporating longer context has been shown to benefit machine translation, but the inclusion of context in end-to-end speech translation (E2E-ST) remains under-studied. To bridge this gap, we introduce target language context in E2E-ST, enhancing coherence and overcoming memory constraints of extended audio segments. Additionally, we propose context dropout to ensure robustness to the absence of context, and further improve performance by adding speaker information. Our proposed contextual E2E-ST outperforms the isolated utterance-based E2E-ST approach. Lastly, we demonstrate that in conversational speech, contextual information primarily contributes to capturing context style, as well as resolving anaphora and named entities.