Search

Visual signals can enhance audiovisual speech recognition accuracy by providing additional contextual information. Given the complexity of visual signals, an audiovisual speech recognition model requires robust generalization capabilities across diverse video scenarios, presenting a significant challenge. In this paper, we introduce EVA, leveraging the mixture-of-Experts for audioVisual ASR to perform robust speech recognition for ``in-the-wild'' videos. Specifically, we first encode visual information into visual tokens sequence and map them into speech space by a lightweight projection. Then, we build EVA upon a robust pretrained speech recognition model, ensuring its generalization ability. Moreover, to incorporate visual information effectively, we inject visual information into the ASR model through a mixture-of-experts module. Experiments show our model achieves state-of-the-art results on three benchmarks, which demonstrates the generalization ability of EVA across diverse video domains., Comment: 6 pages, 2 figures, accepted by IEEE Spoken Language Technology Workshop 2024

In this work, we present SynesLM, an unified model which can perform three multimodal language understanding tasks: audio-visual automatic speech recognition(AV-ASR) and visual-aided speech/machine translation(VST/VMT). Unlike previous research that focused on lip motion as visual cues for speech signals, our work explores more general visual information within entire frames, such as objects and actions. Additionally, we use synthetic image data to enhance the correlation between image and speech data. We benchmark SynesLM against the How2 dataset, demonstrating performance on par with state-of-the-art (SOTA) models dedicated to AV-ASR while maintaining our multitasking framework. Remarkably, for zero-shot AV-ASR, SynesLM achieved SOTA performance by lowering the Word Error Rate (WER) from 43.4% to 39.4% on the VisSpeech Dataset. Furthermore, our results in VST and VMT outperform the previous results, improving the BLEU score to 43.5 from 37.2 for VST, and to 54.8 from 54.4 for VMT.

Speech signals, typically sampled at rates in the tens of thousands per second, contain redundancies, evoking inefficiencies in sequence modeling. High-dimensional speech features such as spectrograms are often used as the input for the subsequent model. However, they can still be redundant. Recent investigations proposed the use of discrete speech units derived from self-supervised learning representations, which significantly compresses the size of speech data. Applying various methods, such as de-duplication and subword modeling, can further compress the speech sequence length. Hence, training time is significantly reduced while retaining notable performance. In this study, we undertake a comprehensive and systematic exploration into the application of discrete units within end-to-end speech processing models. Experiments on 12 automatic speech recognition, 3 speech translation, and 1 spoken language understanding corpora demonstrate that discrete units achieve reasonably good results in almost all the settings. We intend to release our configurations and trained models to foster future research efforts., Comment: Submitted to IEEE ICASSP 2024

Quantum key distribution (QKD) can provide fundamentally proven security for secure communication. Toward application, the secret key rate (SKR) is a key figure of merit for any QKD system. So far, the SKR has been limited to about a few megabit-per-second. Here we report a QKD system that is able to generate key at a record high SKR of 115.8 Mb/s over 10-km standard fibre, and to distribute key over up to 328 km of ultra-low-loss fibre. This attributes to a multi-pixel superconducting nanowire single-photon detector with ultrahigh counting rate, an integrated transmitter that can stably encode polarization states with low error, a fast post-processing algorithm for generating key in real time and the high system clock-rate operation. The results demonstrate the feasibility of practical high-rate QKD with photonic techniques, thus opening its possibility for widespread applications.

This paper studies speculative reasoning task on real-world knowledge graphs (KG) that contain both \textit{false negative issue} (i.e., potential true facts being excluded) and \textit{false positive issue} (i.e., unreliable or outdated facts being included). State-of-the-art methods fall short in the speculative reasoning ability, as they assume the correctness of a fact is solely determined by its presence in KG, making them vulnerable to false negative/positive issues. The new reasoning task is formulated as a noisy Positive-Unlabeled learning problem. We propose a variational framework, namely nPUGraph, that jointly estimates the correctness of both collected and uncollected facts (which we call \textit{label posterior}) and updates model parameters during training. The label posterior estimation facilitates speculative reasoning from two perspectives. First, it improves the robustness of a label posterior-aware graph encoder against false positive links. Second, it identifies missing facts to provide high-quality grounds of reasoning. They are unified in a simple yet effective self-training procedure. Empirically, extensive experiments on three benchmark KG and one Twitter dataset with various degrees of false negative/positive cases demonstrate the effectiveness of nPUGraph., Comment: This paper is accepted by ACL-Findings 2023

Knowledge distillation is an effective paradigm for boosting the performance of pocket-size model, especially when multiple teacher models are available, the student would break the upper limit again. However, it is not economical to train diverse teacher models for the disposable distillation. In this paper, we introduce a new concept dubbed Avatars for distillation, which are the inference ensemble models derived from the teacher. Concretely, (1) For each iteration of distillation training, various Avatars are generated by a perturbation transformation. We validate that Avatars own higher upper limit of working capacity and teaching ability, aiding the student model in learning diverse and receptive knowledge perspectives from the teacher model. (2) During the distillation, we propose an uncertainty-aware factor from the variance of statistical differences between the vanilla teacher and Avatars, to adjust Avatars' contribution on knowledge transfer adaptively. Avatar Knowledge Distillation AKD is fundamentally different from existing methods and refines with the innovative view of unequal training. Comprehensive experiments demonstrate the effectiveness of our Avatars mechanism, which polishes up the state-of-the-art distillation methods for dense prediction without more extra computational cost. The AKD brings at most 0.7 AP gains on COCO 2017 for Object Detection and 1.83 mIoU gains on Cityscapes for Semantic Segmentation, respectively. Code is available at https://github.com/Gumpest/AvatarKD., Comment: Accepted by ACM MM 2023

Although deep learning has significantly improved Face Recognition (FR), dramatic performance deterioration may occur when processing Low Resolution (LR) faces. To alleviate this, approaches based on unified feature space are proposed with the sacrifice under High Resolution (HR) circumstances. To deal with the huge domain gap between HR and LR domains and achieve the best on both domains, we first took a closer look at the impacts of several resolution augmentations and then analyzed the difficulty of LR samples from the perspective of the model gradient produced by different resolution samples. Besides, we also find that the introduction of some resolutions could help the learning of lower resolutions. Based on these, we divide the LR samples into three difficulties according to the resolution and propose a more effective Multi-Resolution Augmentation. Then, due to the rapidly increasing domain gap as the resolution decreases, we carefully design a novel and effective metric loss based on a LogExp distance function that provides decent gradients to prevent oscillation near the convergence point or tolerance to small distance errors; it could also dynamically adjust the penalty for errors in different dimensions, allowing for more optimization of dimensions with large errors. Combining these two insights, our model could learn more general knowledge in a wide resolution range of images and balanced results can be achieved by our extremely simple framework. Moreover, the augmentations and metrics are the cornerstones of LRFR, so our method could be considered a new baseline for the LRFR task. Experiments on the LRFR datasets: SCface, XQLFW, and large-scale LRFR dataset: TinyFace demonstrate the effectiveness of our methods, while the degradation on HRFR datasets is significantly reduced., Comment: AAAI 2023 R2HCAI Workshop

Twin-field quantum key distribution (TF-QKD) has emerged as a promising solution for practical quantum communication over long-haul fiber. However, previous demonstrations on TF-QKD require the phase locking technique to coherently control the twin light fields, inevitably complicating the system with extra fiber channels and peripheral hardware. Here we propose and demonstrate an approach to recover the single-photon interference pattern and realize TF-QKD \emph{without} phase locking. Our approach separates the communication time into reference frames and quantum frames, where the reference frames serve as a flexible scheme for establishing the global phase reference. To do so, we develop a tailored algorithm based on fast Fourier transform to efficiently reconcile the phase reference via data post-processing. We demonstrate no-phase-locking TF-QKD from short to long distances over standard optical fibers. At 50-km standard fiber, we produce a high secret key rate (SKR) of 1.27 Mbit/s, while at 504-km standard fiber, we obtain the repeater-like key rate scaling with a SKR of 34 times higher than the repeaterless secret key capacity. Our work provides a scalable and practical solution to TF-QKD, thus representing an important step towards its wide applications., Comment: Published version

The freeway on-ramp merging section is often identified as a crash-prone spot due to the high frequency of traffic conflicts. Very few traffic conflict analysis studies comprehensively consider different vehicle types at freeway merging section. Thus, the main objective of this study is to analyse conflicts between different vehicle types at freeway merging section. Field data are collected by Unmanned Aerial Vehicle (UAV) at merging areas in Shanghai, China. Vehicle extraction method is utilized to obtain vehicle trajectories. Time-to-collision (TTC) is utilized as the surrogate safety measure. TTC of car-car conflicts are the smallest while TTC of truck-truck conflicts are the largest. Traffic conflicts frequently occur at on-ramp and acceleration lane. Results show the spatial distribution of lane-change conflicts is significantly different between different vehicle types, suggesting that vehicle drivers should maintain safe distance especially car drivers. Besides, in order to decrease lane-change conflict at merging area, traffic management agencies are suggested to change dotted lie to solid lane at the beginning of acceleration lane.

Finding translational biomarkers stands center stage of the future of personalized medicine in healthcare. We observed notable challenges in identifying robust biomarkers as some with great performance in one scenario often fail to perform well in new trials (e.g. different population, indications). With rapid development in the clinical trial world (e.g. assay, disease definition), new trials very likely differ from legacy ones in many perspectives and in development of biomarkers this heterogeneity should be considered. In response, we recommend considering building in the heterogeneity when evaluating biomarkers. In this paper, we present one evaluation strategy by using leave-one-study-out (LOSO) in place of conventional cross-validation (cv) methods to account for the potential heterogeneity across trials used for building and testing the biomarkers. To demonstrate the performance of K-fold vs LOSO cv in estimating the effect size of biomarkers, we leveraged data from clinical trials and simulation studies. In our assessment, LOSO cv provided a more objective estimate of the future performance. This conclusion remained true across different evaluation metrics and different statistical methods., Comment: Paper has 4 pages, 2 figures. Appendix are supplementary at the end