Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

Titanic Calling: Low Bandwidth Video Conference from the Titanic Wreck

Fevziye Irem Eyiokur, Christian Huber, Thai-Binh Nguyen, Tuan-Nam Nguyen, Fabian Retkowski, Enes Yavuz Ugan, Dogucan Yaman, Alexander Waibel

Abstract

In this paper, we report on communication experiments conducted in the summer of 2022 during a deep dive to the wreck of the Titanic. Radio transmission is not possible in deep sea water, and communication links rely on sonar signals. Due to the low bandwidth of sonar signals and the need to communicate readable data, text messaging is used in deep-sea missions. In this paper, we report results and experiences from a messaging system that converts speech to text in a submarine, sends text messages to the surface, and reconstructs those messages as synthetic lip-synchronous videos of the speakers. The resulting system was tested during an actual dive to Titanic in the summer of 2022. We achieved an acceptable latency for a system of such complexity as well as good quality. The system demonstration video can be found at the following link: https://youtu.be/C4lyM86-5Ig

Titanic Calling: Low Bandwidth Video Conference from the Titanic Wreck

Abstract

In this paper, we report on communication experiments conducted in the summer of 2022 during a deep dive to the wreck of the Titanic. Radio transmission is not possible in deep sea water, and communication links rely on sonar signals. Due to the low bandwidth of sonar signals and the need to communicate readable data, text messaging is used in deep-sea missions. In this paper, we report results and experiences from a messaging system that converts speech to text in a submarine, sends text messages to the surface, and reconstructs those messages as synthetic lip-synchronous videos of the speakers. The resulting system was tested during an actual dive to Titanic in the summer of 2022. We achieved an acceptable latency for a system of such complexity as well as good quality. The system demonstration video can be found at the following link: https://youtu.be/C4lyM86-5Ig

Paper Structure

This paper contains 15 sections, 3 figures, 2 tables.

Table of Contents

  1. Introduction
  2. System and Architecture
  3. Speaker Filtering and Segmentation Module
  4. ASR Module
  5. Text Segmentation Module
  6. Multi-Speaker TTS Module
  7. Talking Face Generation Module
  8. Setup
  9. Submersible Side
  10. Top Side (Mother Ship)
  11. Evaluation
  12. Latency
  13. Audio and Video Quality
  14. Conclusion
  15. Impact

Figures (3)

  • Figure 1: Illustration of the proposed system: While the submersible side has the ASR, speech segmentation and filtering systems along with the text segmenter, we have TTS and talking face generation modules on the ship. Communication between the submersible and the ship was done by transmitting the text via sonar communication.
  • Figure 2: Sample images during the usage of the system. (a) Speakers are inside the submersible under the ocean near the Titanic wreck to perform exploration. (b) Audience on the mother ship is communicating via our interface. Our system can provide realistic communication, although the only real communication between the submersible and the ship is just text transmission.
  • Figure 3: Illustration of the submersible communication interface of our system. The interface has been used to display speakers' talk and messages while the submersible dived in Titanic Wreck to 3,800 meters below.