Speech generation for machine dubbing adds complexity to conventional Text-To-Speech solutions as the generated output is required to match the expressiveness, emotion and speaking rate of the source content. Capturing and transferring details and variations in prosody is a challenge. We introduce phrase-level cross-lingual prosody transfer for expressive multi-lingual machine dubbing. The proposed phrase-level prosody transfer delivers a significant 6.2% MUSHRA score increase over a baseline with utterance-level global prosody transfer, thereby closing the gap between the baseline and expressive human dubbing by 23.2%, while preserving intelligibility of the synthesised speech.
Prosody transfer is well-studied in the context of expressive speech synthesis. Cross-lingual prosody transfer, however, is challenging and has been under-explored to date. In this paper, we present a novel solution to learn prosody representations that are transferable across languages and speakers for machine dubbing of expressive multimedia contents. Multimedia contents often contain field recordings. To enable prosody transfer from noisy audios, we introduce a novel noise modelling module that disentangles noise conditioning from prosody conditioning, and thereby gains independent control of noise levels in the synthesised speech. We augment noisy training data with clean data to improve the ability of the model to map the denoised reference audio to clean speech. Our proposed system can generate speech with context-matching prosody and closes the gap between a strong baseline and human expressive dialogs by 11.2%.
Bayesian Neural Networks (BNNs) offer a mathematically grounded framework to quantify the uncertainty of model predictions but come with a prohibitive computation cost for both training and inference. In this work, we show a novel network architecture search (NAS) that optimizes BNNs for both accuracy and uncertainty while having a reduced inference latency. Different from canonical NAS that optimizes solely for in-distribution likelihood, the proposed scheme searches for the uncertainty performance using both in- and out-of-distribution data. Our method is able to search for the correct placement of Bayesian layer(s) in a network. In our experiments, the searched models show comparable uncertainty quantification ability and accuracy compared to the state-of-the-art (deep ensemble). In addition, the searched models use only a fraction of the runtime compared to many popular BNN baselines, reducing the inference runtime cost by $2.98 \times$ and $2.92 \times$ respectively on the CIFAR10 dataset when compared to MCDropout and deep ensemble.
Multi-Modal Self-Supervised Learning from videos has been shown to improve model's performance on various downstream tasks. However, such Self-Supervised pre-training requires large batch sizes and a large amount of computation resources due to the noise present in the uncurated data. This is partly due to the fact that the prevalent training scheme is trained on coarse-grained setting, in which vectors representing the whole video clips or natural language sentences are used for computing similarity. Such scheme makes training noisy as part of the video clips can be totally not correlated with the other-modality input such as text description. In this paper, we propose a fine-grained multi-modal self-supervised training scheme that computes the similarity between embeddings at finer-scale (such as individual feature map embeddings and embeddings of phrases), and uses attention mechanisms to reduce noisy pairs' weighting in the loss function. We show that with the proposed pre-training scheme, we can train smaller models, with smaller batch-size and much less computational resources to achieve downstream tasks performances comparable to State-Of-The-Art, for tasks including action recognition and text-image retrievals.
Abstract reasoning is a key indicator of intelligence. The ability to hypothesise, develop abstract concepts based on concrete observations and apply this hypothesis to justify future actions has been paramount in human development. An existing line of research in outfitting intelligent machines with abstract reasoning capabilities revolves around the Raven's Progressive Matrices (RPM), a multiple-choice visual puzzle where one must identify the missing component which completes the pattern. There have been many breakthroughs in supervised approaches to solving RPM in recent years. However, since this process requires external assistance, we cannot claim that machines have achieved reasoning ability comparable to humans. Namely, when the RPM rule that relations can only exist row/column-wise is properly introduced, humans can solve RPM problems without supervision or prior experience. In this paper, we introduce a pairwise relations discriminator (PRD), a technique to develop unsupervised models with sufficient reasoning abilities to tackle an RPM problem. PRD reframes the RPM problem into a relation comparison task, which we can solve without requiring the labelling of the RPM problem. We can identify the optimal candidate by adapting the application of PRD on the RPM problem. The previous state-of-the-art approach "mcpt" in this domain achieved 28.5% accuracy on the RAVEN dataset "drt", a standard dataset for computational work on RPM. Our approach, the PRD, establishes a new state-of-the-art benchmark with an accuracy of 50.74% on the same dataset, presenting a significant improvement and a step forward in equipping machines with abstract reasoning.
Deep Graph Neural Networks (GNNs) show promising performance on a range of graph tasks, yet at present are costly to run and lack many of the optimisations applied to DNNs. We show, for the first time, how to systematically quantise GNNs with minimal or no loss in performance using Network Architecture Search (NAS). We define the possible quantisation search space of GNNs. The proposed novel NAS mechanism, named Low Precision Graph NAS (LPGNAS), constrains both architecture and quantisation choices to be differentiable. LPGNAS learns the optimal architecture coupled with the best quantisation strategy for different components in the GNN automatically using back-propagation in a single search round. On eight different datasets, solving the task of classifying unseen nodes in a graph, LPGNAS generates quantised models with significant reductions in both model and buffer sizes but with similar accuracy to manually designed networks and other NAS results. In particular, on the Pubmed dataset, LPGNAS shows a better size-accuracy Pareto frontier compared to seven other manual and searched baselines, offering a 2.3 times reduction in model size but a 0.4% increase in accuracy when compared to the best NAS competitor. Finally, from our collected quantisation statistics on a wide range of datasets, we suggest a W4A8 (4-bit weights, 8-bit activations) quantisation strategy might be the bottleneck for naive GNN quantisations.
During the COVID-19 pandemic, rapid and accurate triage of patients at the emergency department is critical to inform decision-making. We propose a data-driven approach for automatic prediction of deterioration risk using a deep neural network that learns from chest X-ray images, and a gradient boosting model that learns from routine clinical variables. Our AI prognosis system, trained using data from 3,661 patients, achieves an AUC of 0.786 (95% CI: 0.742-0.827) when predicting deterioration within 96 hours. The deep neural network extracts informative areas of chest X-ray images to assist clinicians in interpreting the predictions, and performs comparably to two radiologists in a reader study. In order to verify performance in a real clinical setting, we silently deployed a preliminary version of the deep neural network at NYU Langone Health during the first wave of the pandemic, which produced accurate predictions in real-time. In summary, our findings demonstrate the potential of the proposed system for assisting front-line physicians in the triage of COVID-19 patients.
Many meta-learning methods are proposed for few-shot detection. However, previous most methods have two main problems, strong bias between all classes, and poor classification for few-shot classes. Previous works mainly depend on additional datasets and sub-module to alleviate these issues. However, they require more cost. In this paper, we find that the main challenge lies on imbalance between the examples, and poor shared distribution of class-based meta-features. Therefore, we propose a TCL for classification task and a category-based grouping mechanism. The TCL exploits the classification score of true-label class and the classification score of the most similar class to improve detection performance on few-shot classes. According to appearance and environment, the category-based grouping mechanism groups categories into different groupings to promote different similar semantic features more compact, alleviating the strong bias problem and further improving few-shot detection APs. The whole training consists of the base model and the fine-tuning phase. During training detection model, the category-related meta-features are regarded as the weights of the detection layer, exploiting the meta-features with a shared distribution between categories within a group to improve the detection performance. According to grouping mechanism, we group the meta-features vectors, so that the distribution difference between groups is obvious, and the one within each group is less. Experimental results on Pascal VOC dataset demonstrate that ours which combines the TCL with category-based grouping significantly outperforms previous state-of-the-art methods for 1, 2-shot detection, and obtains detection APs of almost 30% for 3-shot detection.