Sign language translation as a kind of technology with profound social significance has attracted growing researchers' interest in recent years. However, the existing sign language translation methods need to read all the videos before starting the translation, which leads to a high inference latency and also limits their application in real-life scenarios. To solve this problem, we propose SimulSLT, the first end-to-end simultaneous sign language translation model, which can translate sign language videos into target text concurrently. SimulSLT is composed of a text decoder, a boundary predictor, and a masked encoder. We 1) use the wait-k strategy for simultaneous translation. 2) design a novel boundary predictor based on the integrate-and-fire module to output the gloss boundary, which is used to model the correspondence between the sign language video and the gloss. 3) propose an innovative re-encode method to help the model obtain more abundant contextual information, which allows the existing video features to interact fully. The experimental results conducted on the RWTH-PHOENIX-Weather 2014T dataset show that SimulSLT achieves BLEU scores that exceed the latest end-to-end non-simultaneous sign language translation model while maintaining low latency, which proves the effectiveness of our method.
Sign language translation (SLT), which generates text in a spoken language from visual content in a sign language, is important to assist the hard-of-hearing community for their communications. Inspired by neural machine translation (NMT), most existing SLT studies adopted a general sequence to sequence learning strategy. However, SLT is significantly different from general NMT tasks since sign languages convey messages through multiple visual-manual aspects. Therefore, in this paper, these unique characteristics of sign languages are formulated as hierarchical spatio-temporal graph representations, including high-level and fine-level graphs of which a vertex characterizes a specified body part and an edge represents their interactions. Particularly, high-level graphs represent the patterns in the regions such as hands and face, and fine-level graphs consider the joints of hands and landmarks of facial regions. To learn these graph patterns, a novel deep learning architecture, namely hierarchical spatio-temporal graph neural network (HST-GNN), is proposed. Graph convolutions and graph self-attentions with neighborhood context are proposed to characterize both the local and the global graph properties. Experimental results on benchmark datasets demonstrated the effectiveness of the proposed method.
In this work, we introduce the BBC-Oxford British Sign Language (BOBSL) dataset, a large-scale video collection of British Sign Language (BSL). BOBSL is an extended and publicly released dataset based on the BSL-1K dataset introduced in previous work. We describe the motivation for the dataset, together with statistics and available annotations. We conduct experiments to provide baselines for the tasks of sign recognition, sign language alignment, and sign language translation. Finally, we describe several strengths and limitations of the data from the perspectives of machine learning and linguistics, note sources of bias present in the dataset, and discuss potential applications of BOBSL in the context of sign language technology. The dataset is available at https://www.robots.ox.ac.uk/~vgg/data/bobsl/.
Automating sign language translation (SLT) is a challenging real world application. Despite its societal importance, though, research progress in the field remains rather poor. Crucially, existing methods that yield viable performance necessitate the availability of laborious to obtain gloss sequence groundtruth. In this paper, we attenuate this need, by introducing an end-to-end SLT model that does not entail explicit use of glosses; the model only needs text groundtruth. This is in stark contrast to existing end-to-end models that use gloss sequence groundtruth, either in the form of a modality that is recognized at an intermediate model stage, or in the form of a parallel output process, jointly trained with the SLT model. Our approach constitutes a Transformer network with a novel type of layers that combines: (i) local winner-takes-all (LWTA) layers with stochastic winner sampling, instead of conventional ReLU layers, (ii) stochastic weights with posterior distributions estimated via variational inference, and (iii) a weight compression technique at inference time that exploits estimated posterior variance to perform massive, almost lossless compression. We demonstrate that our approach can reach the currently best reported BLEU-4 score on the PHOENIX 2014T benchmark, but without making use of glosses for model training, and with a memory footprint reduced by more than 70%.
Despite existing pioneering works on sign language translation (SLT), there is a non-trivial obstacle, i.e., the limited quantity of parallel sign-text data. To tackle this parallel data bottleneck, we propose a sign back-translation (SignBT) approach, which incorporates massive spoken language texts into SLT training. With a text-to-gloss translation model, we first back-translate the monolingual text to its gloss sequence. Then, the paired sign sequence is generated by splicing pieces from an estimated gloss-to-sign bank at the feature level. Finally, the synthetic parallel data serves as a strong supplement for the end-to-end training of the encoder-decoder SLT framework. To promote the SLT research, we further contribute CSL-Daily, a large-scale continuous SLT dataset. It provides both spoken language translations and gloss-level annotations. The topic revolves around people's daily lives (e.g., travel, shopping, medical care), the most likely SLT application scenario. Extensive experimental results and analysis of SLT methods are reported on CSL-Daily. With the proposed sign back-translation method, we obtain a substantial improvement over previous state-of-the-art SLT methods.
Sign language translation (SLT) is often decomposed into video-to-gloss recognition and gloss-to-text translation, where a gloss is a sequence of transcribed spoken-language words in the order in which they are signed. We focus here on gloss-to-text translation, which we treat as a low-resource neural machine translation (NMT) problem. However, unlike traditional low-resource NMT, gloss-to-text translation differs because gloss-text pairs often have a higher lexical overlap and lower syntactic overlap than pairs of spoken languages. We exploit this lexical overlap and handle syntactic divergence by proposing two rule-based heuristics that generate pseudo-parallel gloss-text pairs from monolingual spoken language text. By pre-training on the thus obtained synthetic data, we improve translation from American Sign Language (ASL) to English and German Sign Language (DGS) to German by up to 3.14 and 2.20 BLEU, respectively.
Computational sign language research lacks the large-scale datasets that enables the creation of useful reallife applications. To date, most research has been limited to prototype systems on small domains of discourse, e.g. weather forecasts. To address this issue and to push the field forward, we release six datasets comprised of 190 hours of footage on the larger domain of news. From this, 20 hours of footage have been annotated by Deaf experts and interpreters and is made publicly available for research purposes. In this paper, we share the dataset collection process and tools developed to enable the alignment of sign language video and subtitles, as well as baseline translation results to underpin future research.
Predicting 3D human pose from a single monoscopic video can be highly challenging due to factors such as low resolution, motion blur and occlusion, in addition to the fundamental ambiguity in estimating 3D from 2D. Approaches that directly regress the 3D pose from independent images can be particularly susceptible to these factors and result in jitter, noise and/or inconsistencies in skeletal estimation. Much of which can be overcome if the temporal evolution of the scene and skeleton are taken into account. However, rather than tracking body parts and trying to temporally smooth them, we propose a novel transformer based network that can learn a distribution over both pose and motion in an unsupervised fashion. We call our approach Skeletor. Skeletor overcomes inaccuracies in detection and corrects partial or entire skeleton corruption. Skeletor uses strong priors learn from on 25 million frames to correct skeleton sequences smoothly and consistently. Skeletor can achieve this as it implicitly learns the spatio-temporal context of human motion via a transformer based neural network. Extensive experiments show that Skeletor achieves improved performance on 3D human pose estimation and further provides benefits for downstream tasks such as sign language translation.
New deep-learning architectures are created every year, achieving state-of-the-art results in image recognition and leading to the belief that, in a few years, complex tasks such as sign language translation will be considerably easier, serving as a communication tool for the hearing-impaired community. On the other hand, these algorithms still need a lot of data to be trained and the dataset creation process is expensive, time-consuming, and slow. Thereby, this work aims to investigate techniques of digital image processing and machine learning that can be used to create a sign language dataset effectively. We argue about data acquisition, such as the frames per second rate to capture or subsample the videos, the background type, preprocessing, and data augmentation, using convolutional neural networks and object detection to create an image classifier and comparing the results based on statistical tests. Different datasets were created to test the hypotheses, containing 14 words used daily and recorded by different smartphones in the RGB color system. We achieved an accuracy of 96.38% on the test set and 81.36% on the validation set containing more challenging conditions, showing that 30 FPS is the best frame rate subsample to train the classifier, geometric transformations work better than intensity transformations, and artificial background creation is not effective to model generalization. These trade-offs should be considered in future work as a cost-benefit guideline between computational cost and accuracy gain when creating a dataset and training a sign recognition model.
Memory-efficient continuous Sign Language Translation is a significant challenge for the development of assisted technologies with real-time applicability for the deaf. In this work, we introduce a paradigm of designing recurrent deep networks whereby the output of the recurrent layer is derived from appropriate arguments from nonparametric statistics. A novel variational Bayesian sequence-to-sequence network architecture is proposed that consists of a) a full Gaussian posterior distribution for data-driven memory compression and b) a nonparametric Indian Buffet Process prior for regularization applied on the Gated Recurrent Unit non-gate weights. We dub our approach Stick-Breaking Recurrent network and show that it can achieve a substantial weight compression without diminishing modeling performance.
In this thesis, we propose a multitask learning based method to improve Neural Sign Language Translation (NSLT) consisting of two parts, a tokenization layer and Neural Machine Translation (NMT). The tokenization part focuses on how Sign Language (SL) videos should be represented to be fed into the other part. It has not been studied elaborately whereas NMT research has attracted several researchers contributing enormous advancements. Up to now, there are two main input tokenization levels, namely frame-level and gloss-level tokenization. Glosses are world-like intermediate presentation and unique to SLs. Therefore, we aim to develop a generic sign-level tokenization layer so that it is applicable to other domains without further effort. We begin with investigating current tokenization approaches and explain their weaknesses with several experiments. To provide a solution, we adapt Transfer Learning, Multitask Learning and Unsupervised Domain Adaptation into this research to leverage additional supervision. We succeed in enabling knowledge transfer between SLs and improve translation quality by 5 points in BLEU-4 and 8 points in ROUGE scores. Secondly, we show the effects of body parts by extensive experiments in all the tokenization approaches. Apart from these, we adopt 3D-CNNs to improve efficiency in terms of time and space. Lastly, we discuss the advantages of sign-level tokenization over gloss-level tokenization. To sum up, our proposed method eliminates the need for gloss level annotation to obtain higher scores by providing additional supervision by utilizing weak supervision sources.
Sign language translation (SLT) aims to interpret sign video sequences into text-based natural language sentences. Sign videos consist of continuous sequences of sign gestures with no clear boundaries in between. Existing SLT models usually represent sign visual features in a frame-wise manner so as to avoid needing to explicitly segmenting the videos into isolated signs. However, these methods neglect the temporal information of signs and lead to substantial ambiguity in translation. In this paper, we explore the temporal semantic structures of signvideos to learn more discriminative features. To this end, we first present a novel sign video segment representation which takes into account multiple temporal granularities, thus alleviating the need for accurate video segmentation. Taking advantage of the proposed segment representation, we develop a novel hierarchical sign video feature learning method via a temporal semantic pyramid network, called TSPNet. Specifically, TSPNet introduces an inter-scale attention to evaluate and enhance local semantic consistency of sign segments and an intra-scale attention to resolve semantic ambiguity by using non-local video context. Experiments show that our TSPNet outperforms the state-of-the-art with significant improvements on the BLEU score (from 9.58 to 13.41) and ROUGE score (from 31.80 to 34.96)on the largest commonly-used SLT dataset. Our implementation is available at https://github.com/verashira/TSPNet.
Sign Languages are expressed through hand and upper body gestures as well as facial expressions. Therefore, Sign Language Recognition (SLR) needs to focus on all such cues. Previous work uses hand-crafted mechanisms or network aggregation to extract the different cue features, to increase SLR performance. This is slow and involves complicated architectures. We propose a more straightforward approach that focuses on training separate cue models specializing on the dominant hand, hands, face, and upper body regions. We compare the performance of 3D Convolutional Neural Network (CNN) models specializing in these regions, combine them through score-level fusion, and use the weighted alternative. Our experimental results have shown the effectiveness of mixed convolutional models. Their fusion yields up to 19% accuracy improvement over the baseline using the full upper body. Furthermore, we include a discussion for fusion settings, which can help future work on Sign Language Translation (SLT).
Sign languages use multiple asynchronous information channels (articulators), not just the hands but also the face and body, which computational approaches often ignore. In this paper we tackle the multi-articulatory sign language translation task and propose a novel multi-channel transformer architecture. The proposed architecture allows both the inter and intra contextual relationships between different sign articulators to be modelled within the transformer network itself, while also maintaining channel specific information. We evaluate our approach on the RWTH-PHOENIX-Weather-2014T dataset and report competitive translation performance. Importantly, we overcome the reliance on gloss annotations which underpin other state-of-the-art approaches, thereby removing future need for expensive curated datasets.
One of the factors that have hindered progress in the areas of sign language recognition, translation, and production is the absence of large annotated datasets. Towards this end, we introduce How2Sign, a multimodal and multiview continuous American Sign Language (ASL) dataset, consisting of a parallel corpus of more than 80 hours of sign language videos and a set of corresponding modalities including speech, English transcripts, and depth. A three-hour subset was further recorded in the Panoptic studio enabling detailed 3D pose estimation. To evaluate the potential of How2Sign for real-world impact, we conduct a study with ASL signers and show that synthesized videos using our dataset can indeed be understood. The study further gives insights on challenges that computer vision should address in order to make progress in this field. Dataset website: http://how2sign.github.io/
Advancements in gesture recognition algorithms have led to a significant growth in sign language translation. By making use of efficient intelligent models, signs can be recognized with precision. The proposed work presents a novel one-dimensional Convolutional Neural Network (CNN) array architecture for recognition of signs from the Indian sign language using signals recorded from a custom designed wearable IMU device. The IMU device makes use of tri-axial accelerometer and gyroscope. The signals recorded using the IMU device are segregated on the basis of their context, such as whether they correspond to signing for a general sentence or an interrogative sentence. The array comprises of two individual CNNs, one classifying the general sentences and the other classifying the interrogative sentence. Performances of individual CNNs in the array architecture are compared to that of a conventional CNN classifying the unsegregated dataset. Peak classification accuracies of 94.20% for general sentences and 95.00% for interrogative sentences achieved with the proposed CNN array in comparison to 93.50% for conventional CNN assert the suitability of the proposed approach.
In the past decades the set of human tasks that are solved by machines was extended dramatically. From simple image classification problems researchers now move towards solving more sophisticated and vital problems, like, autonomous driving and language translation. The case of language translation includes a challenging area of sign language translation that incorporates both image and language processing. We make a step in that direction by proposing a lightweight network for ASL gesture recognition with a performance sufficient for practical applications. The proposed solution demonstrates impressive robustness on MS-ASL dataset and in live mode for continuous sign gesture recognition scenario. Additionally, we describe how to combine action recognition model training with metric-learning to train the network on the database of limited size. The training code is available as part of Intel OpenVINO Training Extensions.
Sign Language Translation (SLT) first uses a Sign Language Recognition (SLR) system to extract sign language glosses from videos. Then, a translation system generates spoken language translations from the sign language glosses. This paper focuses on the translation system and introduces the STMC-Transformer which improves on the current state-of-the-art by over 5 and 7 BLEU respectively on gloss-to-text and video-to-text translation of the PHOENIX-Weather 2014T dataset. On the ASLG-PC12 corpus, we report an increase of over 16 BLEU. We also demonstrate the problem in current methods that rely on gloss supervision. The video-to-text translation of our STMC-Transformer outperforms translation of GT glosses. This contradicts previous claims that GT gloss translation acts as an upper bound for SLT performance and reveals that glosses are an inefficient representation of sign language. For future SLT research, we therefore suggest an end-to-end training of the recognition and translation models, or using a different sign language annotation scheme.
Prior work on Sign Language Translation has shown that having a mid-level sign gloss representation (effectively recognizing the individual signs) improves the translation performance drastically. In fact, the current state-of-the-art in translation requires gloss level tokenization in order to work. We introduce a novel transformer based architecture that jointly learns Continuous Sign Language Recognition and Translation while being trainable in an end-to-end manner. This is achieved by using a Connectionist Temporal Classification (CTC) loss to bind the recognition and translation problems into a single unified architecture. This joint approach does not require any ground-truth timing information, simultaneously solving two co-dependant sequence-to-sequence learning problems and leads to significant performance gains. We evaluate the recognition and translation performances of our approaches on the challenging RWTH-PHOENIX-Weather-2014T (PHOENIX14T) dataset. We report state-of-the-art sign language recognition and translation results achieved by our Sign Language Transformers. Our translation networks outperform both sign video to spoken language and gloss to spoken language translation models, in some cases more than doubling the performance (9.58 vs. 21.80 BLEU-4 Score). We also share new baseline translation results using transformer networks for several other text-to-text sign language translation tasks.
Sign Language Translation has attained considerable success recently, raising hopes for improved communication with the Deaf. A pre-processing step called tokenization improves the success of translations. Tokens can be learned from sign videos if supervised data is available. However, data annotation at the gloss level is costly, and annotated data is scarce. The paper utilizes Adversarial, Multitask, Transfer Learning to search for semi-supervised tokenization approaches without burden of additional labeling. It provides extensive experiments to compare all the methods in different settings to conduct a deeper analysis. In the case of no additional target annotation besides sentences, the proposed methodology attains 13.25 BLUE-4 and 36.28 ROUGE scores which improves the current state-of-the-art by 4 points in BLUE-4 and 5 points in ROUGE.