Sorry, you need to enable JavaScript to visit this website.

Enhancing End-to-End Conversational Speech Translation Through Target Language Context Utilization

DOI:
10.60864/7k2s-zs80
Citation Author(s):
Amir Hussein, Brian Yan, Antonios Anastasopoulos, Shinji Watanabe, Sanjeev Khudanpur
Submitted by:
Amir Hussein
Last updated:
6 June 2024 - 10:54am
Document Type:
Poster
Categories:
 

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.

up
0 users have voted: