University of Surrey
Abstract:Lip Reading, or Visual Automatic Speech Recognition (V-ASR), is a complex task requiring the interpretation of spoken language exclusively from visual cues, primarily lip movements and facial expressions. This task is especially challenging due to the absence of auditory information and the inherent ambiguity when visually distinguishing phonemes that have overlapping visemes where different phonemes appear identical on the lips. Current methods typically attempt to predict words or characters directly from these visual cues, but this approach frequently encounters high error rates due to coarticulation effects and viseme ambiguity. We propose a novel two-stage, phoneme-centric framework for Visual Automatic Speech Recognition (V-ASR) that addresses these longstanding challenges. First, our model predicts a compact sequence of phonemes from visual inputs using a Video Transformer with a CTC head, thereby reducing the task complexity and achieving robust speaker invariance. This phoneme output then serves as the input to a fine-tuned Large Language Model (LLM), which reconstructs coherent words and sentences by leveraging broader linguistic context. Unlike existing methods that either predict words directly-often faltering on visually similar phonemes-or rely on large-scale multimodal pre-training, our approach explicitly encodes intermediate linguistic structure while remaining highly data efficient. We demonstrate state-of-the-art performance on two challenging datasets, LRS2 and LRS3, where our method achieves significant reductions in Word Error Rate (WER) achieving a SOTA WER of 18.7 on LRS3 despite using 99.4% less labelled data than the next best approach.
Abstract:Sign language representation learning presents unique challenges due to the complex spatio-temporal nature of signs and the scarcity of labeled datasets. Existing methods often rely either on models pre-trained on general visual tasks, that lack sign-specific features, or use complex multimodal and multi-branch architectures. To bridge this gap, we introduce a scalable, self-supervised framework for sign representation learning. We leverage important inductive (sign) priors during the training of our RGB model. To do this, we leverage simple but important cues based on skeletons while pretraining a masked autoencoder. These sign specific priors alongside feature regularization and an adversarial style agnostic loss provide a powerful backbone. Notably, our model does not require skeletal keypoints during inference, avoiding the limitations of keypoint-based models during downstream tasks. When finetuned, we achieve state-of-the-art performance for sign recognition on the WLASL, ASL-Citizen and NMFs-CSL datasets, using a simpler architecture and with only a single-modality. Beyond recognition, our frozen model excels in sign dictionary retrieval and sign translation, surpassing standard MAE pretraining and skeletal-based representations in retrieval. It also reduces computational costs for training existing sign translation models while maintaining strong performance on Phoenix2014T, CSL-Daily and How2Sign.
Abstract:As robots increasingly coexist with humans, they must navigate complex, dynamic environments rich in visual information and implicit social dynamics, like when to yield or move through crowds. Addressing these challenges requires significant advances in vision-based sensing and a deeper understanding of socio-dynamic factors, particularly in tasks like navigation. To facilitate this, robotics researchers need advanced simulation platforms offering dynamic, photorealistic environments with realistic actors. Unfortunately, most existing simulators fall short, prioritizing geometric accuracy over visual fidelity, and employing unrealistic agents with fixed trajectories and low-quality visuals. To overcome these limitations, we developed a simulator that incorporates three essential elements: (1) photorealistic neural rendering of environments, (2) neurally animated human entities with behavior management, and (3) an ego-centric robotic agent providing multi-sensor output. By utilizing advanced neural rendering techniques in a dual-NeRF simulator, our system produces high-fidelity, photorealistic renderings of both environments and human entities. Additionally, it integrates a state-of-the-art Social Force Model to model dynamic human-human and human-robot interactions, creating the first photorealistic and accessible human-robot simulation system powered by neural rendering.
Abstract:Sign Language Assessment (SLA) tools are useful to aid in language learning and are underdeveloped. Previous work has focused on isolated signs or comparison against a single reference video to assess Sign Languages (SL). This paper introduces a novel SLA tool designed to evaluate the comprehensibility of SL by modelling the natural distribution of human motion. We train our pipeline on data from native signers and evaluate it using SL learners. We compare our results to ratings from a human raters study and find strong correlation between human ratings and our tool. We visually demonstrate our tools ability to detect anomalous results spatio-temporally, providing actionable feedback to aid in SL learning and assessment.
Abstract:This paper addresses the problem of diversity-aware sign language production, where we want to give an image (or sequence) of a signer and produce another image with the same pose but different attributes (\textit{e.g.} gender, skin color). To this end, we extend the variational inference paradigm to include information about the pose and the conditioning of the attributes. This formulation improves the quality of the synthesised images. The generator framework is presented as a UNet architecture to ensure spatial preservation of the input pose, and we include the visual features from the variational inference to maintain control over appearance and style. We generate each body part with a separate decoder. This architecture allows the generator to deliver better overall results. Experiments on the SMILE II dataset show that the proposed model performs quantitatively better than state-of-the-art baselines regarding diversity, per-pixel image quality, and pose estimation. Quantitatively, it faithfully reproduces non-manual features for signers.
Abstract:Sign Language Production (SLP) is a challenging task, given the limited resources available and the inherent diversity within sign data. As a result, previous works have suffered from the problem of regression to the mean, leading to under-articulated and incomprehensible signing. In this paper, we propose using dictionary examples and a learnt codebook of facial expressions to create expressive sign language sequences. However, simply concatenating signs and adding the face creates robotic and unnatural sequences. To address this we present a 7-step approach to effectively stitch sequences together. First, by normalizing each sign into a canonical pose, cropping, and stitching we create a continuous sequence. Then, by applying filtering in the frequency domain and resampling each sign, we create cohesive natural sequences that mimic the prosody found in the original data. We leverage a SignGAN model to map the output to a photo-realistic signer and present a complete Text-to-Sign (T2S) SLP pipeline. Our evaluation demonstrates the effectiveness of the approach, showcasing state-of-the-art performance across all datasets. Finally, a user evaluation shows our approach outperforms the baseline model and is capable of producing realistic sign language sequences.
Abstract:Automatic Sign Language Translation requires the integration of both computer vision and natural language processing to effectively bridge the communication gap between sign and spoken languages. However, the deficiency in large-scale training data to support sign language translation means we need to leverage resources from spoken language. We introduce, Sign2GPT, a novel framework for sign language translation that utilizes large-scale pretrained vision and language models via lightweight adapters for gloss-free sign language translation. The lightweight adapters are crucial for sign language translation, due to the constraints imposed by limited dataset sizes and the computational requirements when training with long sign videos. We also propose a novel pretraining strategy that directs our encoder to learn sign representations from automatically extracted pseudo-glosses without requiring gloss order information or annotations. We evaluate our approach on two public benchmark sign language translation datasets, namely RWTH-PHOENIX-Weather 2014T and CSL-Daily, and improve on state-of-the-art gloss-free translation performance with a significant margin.
Abstract:This paper discusses the results of the third edition of the Monocular Depth Estimation Challenge (MDEC). The challenge focuses on zero-shot generalization to the challenging SYNS-Patches dataset, featuring complex scenes in natural and indoor settings. As with the previous edition, methods can use any form of supervision, i.e. supervised or self-supervised. The challenge received a total of 19 submissions outperforming the baseline on the test set: 10 among them submitted a report describing their approach, highlighting a diffused use of foundational models such as Depth Anything at the core of their method. The challenge winners drastically improved 3D F-Score performance, from 17.51% to 23.72%.
Abstract:Sign languages, often categorised as low-resource languages, face significant challenges in achieving accurate translation due to the scarcity of parallel annotated datasets. This paper introduces Select and Reorder (S&R), a novel approach that addresses data scarcity by breaking down the translation process into two distinct steps: Gloss Selection (GS) and Gloss Reordering (GR). Our method leverages large spoken language models and the substantial lexical overlap between source spoken languages and target sign languages to establish an initial alignment. Both steps make use of Non-AutoRegressive (NAR) decoding for reduced computation and faster inference speeds. Through this disentanglement of tasks, we achieve state-of-the-art BLEU and Rouge scores on the Meine DGS Annotated (mDGS) dataset, demonstrating a substantial BLUE-1 improvement of 37.88% in Text to Gloss (T2G) Translation. This innovative approach paves the way for more effective translation models for sign languages, even in resource-constrained settings.
Abstract:Phonetic representations are used when recording spoken languages, but no equivalent exists for recording signed languages. As a result, linguists have proposed several annotation systems that operate on the gloss or sub-unit level; however, these resources are notably irregular and scarce. Sign Language Production (SLP) aims to automatically translate spoken language sentences into continuous sequences of sign language. However, current state-of-the-art approaches rely on scarce linguistic resources to work. This has limited progress in the field. This paper introduces an innovative solution by transforming the continuous pose generation problem into a discrete sequence generation problem. Thus, overcoming the need for costly annotation. Although, if available, we leverage the additional information to enhance our approach. By applying Vector Quantisation (VQ) to sign language data, we first learn a codebook of short motions that can be combined to create a natural sequence of sign. Where each token in the codebook can be thought of as the lexicon of our representation. Then using a transformer we perform a translation from spoken language text to a sequence of codebook tokens. Each token can be directly mapped to a sequence of poses allowing the translation to be performed by a single network. Furthermore, we present a sign stitching method to effectively join tokens together. We evaluate on the RWTH-PHOENIX-Weather-2014T (PHOENIX14T) and the more challenging Meine DGS Annotated (mDGS) datasets. An extensive evaluation shows our approach outperforms previous methods, increasing the BLEU-1 back translation score by up to 72%.