A Simple Baseline for Spoken Language to Sign Language Translation with 3D Avatars

TL;DR

This paper introduces a simple baseline method for translating spoken language into sign language using 3D avatars, leveraging a gloss-video dictionary and sign rendering, pioneering the 3D sign output format.

Contribution

The paper presents the first Spoken2Sign translation system with 3D sign output, combining a gloss-video dictionary, 3D sign estimation, and a translation model.

Findings

First to demonstrate Spoken2Sign with 3D sign output

3D keypoint augmentation improves sign understanding

Multi-view understanding enhances translation accuracy

Abstract

The objective of this paper is to develop a functional system for translating spoken languages into sign languages, referred to as Spoken2Sign translation. The Spoken2Sign task is orthogonal and complementary to traditional sign language to spoken language (Sign2Spoken) translation. To enable Spoken2Sign translation, we present a simple baseline consisting of three steps: 1) creating a gloss-video dictionary using existing Sign2Spoken benchmarks; 2) estimating a 3D sign for each sign video in the dictionary; 3) training a Spoken2Sign model, which is composed of a Text2Gloss translator, a sign connector, and a rendering module, with the aid of the yielded gloss-3D sign dictionary. The translation results are then displayed through a sign avatar. As far as we know, we are the first to present the Spoken2Sign task in an output format of 3D signs. In addition to its capability of Spoken2Sign translation, we also demonstrate that two by-products of our approach-3D keypoint augmentation and multi-view understanding-can assist in keypoint-based sign language understanding. Code and models are available at https://github.com/FangyunWei/SLRT.