Sentence-Level Sign Language Recognition Framework

TL;DR

This paper introduces two sentence-level sign language recognition models using CTC, one based on LRCN and the other on a Multi-Cue Network, achieving a 35% WER on RWTH-PHOENIX-Weather.

Contribution

The paper proposes novel sentence-level SLR models leveraging CTC and multi-cue features, improving recognition accuracy without prior knowledge.

Findings

Achieved 35% Word Error Rate on RWTH-PHOENIX-Weather.

Compared LRCN-based and multi-cue models for SLR.

Demonstrated effectiveness of multi-cue features in sign language recognition.

Abstract

We present two solutions to sentence-level SLR. Sentence-level SLR required mapping videos of sign language sentences to sequences of gloss labels. Connectionist Temporal Classification (CTC) has been used as the classifier level of both models. CTC is used to avoid pre-segmenting the sentences into individual words. The first model is an LRCN-based model, and the second model is a Multi-Cue Network. LRCN is a model in which a CNN as a feature extractor is applied to each frame before feeding them into an LSTM. In the first approach, no prior knowledge has been leveraged. Raw frames are fed into an 18-layer LRCN with a CTC on top. In the second approach, three main characteristics (hand shape, hand position, and hand movement information) associated with each sign have been extracted using Mediapipe. 2D landmarks of hand shape have been used to create the skeleton of the hands and then are fed to a CONV-LSTM model. Hand locations and hand positions as relative distance to head are fed to separate LSTMs. All three sources of information have been then integrated into a Multi-Cue network with a CTC classification layer. We evaluated the performance of proposed models on RWTH-PHOENIX-Weather. After performing an excessive search on model hyper-parameters such as the number of feature maps, input size, batch size, sequence length, LSTM memory cell, regularization, and dropout, we were able to achieve 35 Word Error Rate (WER).