Personal assistants, automatic speech recognizers and dialogue understanding systems are becoming more critical in our interconnected digital world. A clear example is air traffic control (ATC) communications. ATC aims at guiding aircraft and controlling the airspace in a safe and optimal manner. These voice-based dialogues are carried between an air traffic controller (ATCO) and pilots via very-high frequency radio channels. In order to incorporate these novel technologies into ATC (low-resource domain), large-scale annotated datasets are required to develop the data-driven AI systems. Two examples are automatic speech recognition (ASR) and natural language understanding (NLU). In this paper, we introduce the ATCO2 corpus, a dataset that aims at fostering research on the challenging ATC field, which has lagged behind due to lack of annotated data. The ATCO2 corpus covers 1) data collection and pre-processing, 2) pseudo-annotations of speech data, and 3) extraction of ATC-related named entities. The ATCO2 corpus is split into three subsets. 1) ATCO2-test-set corpus contains 4 hours of ATC speech with manual transcripts and a subset with gold annotations for named-entity recognition (callsign, command, value). 2) The ATCO2-PL-set corpus consists of 5281 hours of unlabeled ATC data enriched with automatic transcripts from an in-domain speech recognizer, contextual information, speaker turn information, signal-to-noise ratio estimate and English language detection score per sample. Both available for purchase through ELDA at http://catalog.elra.info/en-us/repository/browse/ELRA-S0484. 3) The ATCO2-test-set-1h corpus is a one-hour subset from the original test set corpus, that we are offering for free at https://www.atco2.org/data. We expect the ATCO2 corpus will foster research on robust ASR and NLU not only in the field of ATC communications but also in the general research community.

最近，盲目的语音分离（BSS）和目标语音提取（TSE）的表现已取得了长足的进步。但是，大多数作品都专注于相对控制的条件，例如阅读语音。在更现实的情况下，性能可能会降低。引起这种降解的因素之一可能是固有的说话者变异性，例如情绪，通常在现实的语音中发生。在本文中，我们研究了情绪对TSE和BSS的影响。我们创建了一个新的测试数据集，以评估TSE和BSS。该数据集结合了Librispeech和Ryerson Audio-Visual Visual Espections and Song（Ravdess）。通过受控的实验，我们可以分析不同情绪对BSS和TSE性能的影响。我们观察到BSS对情绪相对强大，而TSE需要识别和提取目标说话者的语音，对情绪更为敏感。在比较演讲者验证实验中，我们表明，在处理情感语音时，确定目标扬声器可能特别具有挑战性。使用我们的发现，我们概述了可能改善BSS和TSE系统对情感语音的鲁棒性的潜在方向。

通过未计算的数据情况和缺乏本领域缺乏标准基准的动机，我们补充了我们以前的努力，并提出了一个专为培训和评估文本无关的多通道扬声器验证系统的全面语料库。还可以容易地用于DERE失去，去噪和语音增强的实验。我们通过利用VOXECEB数据集的清洁部分顶部的数据仿真来解决缺乏多通道训练数据的缺乏问题。开发和评估试验基于复杂的传统的声音，这些声音在复杂的环境环境（声音）语料库中，我们修改以提供多渠道试验。我们发布从公共来源创建数据集的完整食谱作为Multisv语料库，我们提供了两种多通道扬声器验证系统，其中两个多通道扬声器验证系统，基于神经网络的波束成形，基于预测理想二进制掩码或更新的CONV-TASNet更新。

在典型的多讲话者语音识别系统中，基于神经网络的声学模型预测每个扬声器的Senone状态后部。这些稍后被单通讲话者解码器用来分别在每个扬声器特定的输出流上应用。在这项工作中，我们认为这样的计划是次优的，并提出一个原理的解决方案，该原则解决方案共同解码所有发言人。我们修改了声学模型以预测所有扬声器的联合状态后索，使网络能够表达对扬声器的零件归属的不确定性。我们采用联合解码器，可以与更高级别的语言信息一起使用这种不确定性。为此，我们在早期多讲话者语音识别系统中重新访问阶乘生成模型中使用的解码算法。与这些早期作品相比，我们用DNN替换GMM声学模型，提供更大的建模电力并简化了推理的一部分。我们展示了在混合Tidigits DataSet上对概念实验证明的关节解码的优势。

Modeling lies at the core of both the financial and the insurance industry for a wide variety of tasks. The rise and development of machine learning and deep learning models have created many opportunities to improve our modeling toolbox. Breakthroughs in these fields often come with the requirement of large amounts of data. Such large datasets are often not publicly available in finance and insurance, mainly due to privacy and ethics concerns. This lack of data is currently one of the main hurdles in developing better models. One possible option to alleviating this issue is generative modeling. Generative models are capable of simulating fake but realistic-looking data, also referred to as synthetic data, that can be shared more freely. Generative Adversarial Networks (GANs) is such a model that increases our capacity to fit very high-dimensional distributions of data. While research on GANs is an active topic in fields like computer vision, they have found limited adoption within the human sciences, like economics and insurance. Reason for this is that in these fields, most questions are inherently about identification of causal effects, while to this day neural networks, which are at the center of the GAN framework, focus mostly on high-dimensional correlations. In this paper we study the causal preservation capabilities of GANs and whether the produced synthetic data can reliably be used to answer causal questions. This is done by performing causal analyses on the synthetic data, produced by a GAN, with increasingly more lenient assumptions. We consider the cross-sectional case, the time series case and the case with a complete structural model. It is shown that in the simple cross-sectional scenario where correlation equals causation the GAN preserves causality, but that challenges arise for more advanced analyses.

Deep learning models are known to put the privacy of their training data at risk, which poses challenges for their safe and ethical release to the public. Differentially private stochastic gradient descent is the de facto standard for training neural networks without leaking sensitive information about the training data. However, applying it to models for graph-structured data poses a novel challenge: unlike with i.i.d. data, sensitive information about a node in a graph cannot only leak through its gradients, but also through the gradients of all nodes within a larger neighborhood. In practice, this limits privacy-preserving deep learning on graphs to very shallow graph neural networks. We propose to solve this issue by training graph neural networks on disjoint subgraphs of a given training graph. We develop three random-walk-based methods for generating such disjoint subgraphs and perform a careful analysis of the data-generating distributions to provide strong privacy guarantees. Through extensive experiments, we show that our method greatly outperforms the state-of-the-art baseline on three large graphs, and matches or outperforms it on four smaller ones.

Data-driven models such as neural networks are being applied more and more to safety-critical applications, such as the modeling and control of cyber-physical systems. Despite the flexibility of the approach, there are still concerns about the safety of these models in this context, as well as the need for large amounts of potentially expensive data. In particular, when long-term predictions are needed or frequent measurements are not available, the open-loop stability of the model becomes important. However, it is difficult to make such guarantees for complex black-box models such as neural networks, and prior work has shown that model stability is indeed an issue. In this work, we consider an aluminum extraction process where measurements of the internal state of the reactor are time-consuming and expensive. We model the process using neural networks and investigate the role of including skip connections in the network architecture as well as using l1 regularization to induce sparse connection weights. We demonstrate that these measures can greatly improve both the accuracy and the stability of the models for datasets of varying sizes.

Machine learning models are typically evaluated by computing similarity with reference annotations and trained by maximizing similarity with such. Especially in the bio-medical domain, annotations are subjective and suffer from low inter- and intra-rater reliability. Since annotations only reflect the annotation entity's interpretation of the real world, this can lead to sub-optimal predictions even though the model achieves high similarity scores. Here, the theoretical concept of Peak Ground Truth (PGT) is introduced. PGT marks the point beyond which an increase in similarity with the reference annotation stops translating to better Real World Model Performance (RWMP). Additionally, a quantitative technique to approximate PGT by computing inter- and intra-rater reliability is proposed. Finally, three categories of PGT-aware strategies to evaluate and improve model performance are reviewed.

Explainable AI transforms opaque decision strategies of ML models into explanations that are interpretable by the user, for example, identifying the contribution of each input feature to the prediction at hand. Such explanations, however, entangle the potentially multiple factors that enter into the overall complex decision strategy. We propose to disentangle explanations by finding relevant subspaces in activation space that can be mapped to more abstract human-understandable concepts and enable a joint attribution on concepts and input features. To automatically extract the desired representation, we propose new subspace analysis formulations that extend the principle of PCA and subspace analysis to explanations. These novel analyses, which we call principal relevant component analysis (PRCA) and disentangled relevant subspace analysis (DRSA), optimize relevance of projected activations rather than the more traditional variance or kurtosis. This enables a much stronger focus on subspaces that are truly relevant for the prediction and the explanation, in particular, ignoring activations or concepts to which the prediction model is invariant. Our approach is general enough to work alongside common attribution techniques such as Shapley Value, Integrated Gradients, or LRP. Our proposed methods show to be practically useful and compare favorably to the state of the art as demonstrated on benchmarks and three use cases.

Cybercriminals are moving towards zero-day attacks affecting resource-constrained devices such as single-board computers (SBC). Assuming that perfect security is unrealistic, Moving Target Defense (MTD) is a promising approach to mitigate attacks by dynamically altering target attack surfaces. Still, selecting suitable MTD techniques for zero-day attacks is an open challenge. Reinforcement Learning (RL) could be an effective approach to optimize the MTD selection through trial and error, but the literature fails when i) evaluating the performance of RL and MTD solutions in real-world scenarios, ii) studying whether behavioral fingerprinting is suitable for representing SBC's states, and iii) calculating the consumption of resources in SBC. To improve these limitations, the work at hand proposes an online RL-based framework to learn the correct MTD mechanisms mitigating heterogeneous zero-day attacks in SBC. The framework considers behavioral fingerprinting to represent SBCs' states and RL to learn MTD techniques that mitigate each malicious state. It has been deployed on a real IoT crowdsensing scenario with a Raspberry Pi acting as a spectrum sensor. More in detail, the Raspberry Pi has been infected with different samples of command and control malware, rootkits, and ransomware to later select between four existing MTD techniques. A set of experiments demonstrated the suitability of the framework to learn proper MTD techniques mitigating all attacks (except a harmfulness rootkit) while consuming <1 MB of storage and utilizing <55% CPU and <80% RAM.