MeetDot: Videoconferencing with Live Translation Captions

TL;DR

MeetDot is a videoconferencing system that provides live translation captions in multiple languages, aiming to improve multilingual communication by integrating ASR and MT with user-friendly features and evaluation tools.

Contribution

The paper introduces MeetDot, a modular, open-source videoconferencing system with real-time translation captions, optimized for low latency and user experience, and includes novel evaluation metrics.

Findings

Supports 4 languages with integrated ASR and MT

Features smooth scrolling and flicker reduction for better user experience

Includes an innovative cross-lingual word-guessing game for system evaluation

Abstract

We present MeetDot, a videoconferencing system with live translation captions overlaid on screen. The system aims to facilitate conversation between people who speak different languages, thereby reducing communication barriers between multilingual participants. Currently, our system supports speech and captions in 4 languages and combines automatic speech recognition (ASR) and machine translation (MT) in a cascade. We use the re-translation strategy to translate the streamed speech, resulting in caption flicker. Additionally, our system has very strict latency requirements to have acceptable call quality. We implement several features to enhance user experience and reduce their cognitive load, such as smooth scrolling captions and reducing caption flicker. The modular architecture allows us to integrate different ASR and MT services in our backend. Our system provides an integrated evaluation suite to optimize key intrinsic evaluation metrics such as accuracy, latency and erasure. Finally, we present an innovative cross-lingual word-guessing game as an extrinsic evaluation metric to measure end-to-end system performance. We plan to make our system open-source for research purposes.