In February of 2013, Eric Loomis was driving around in the small town of La Crosse in Wisconsin, US, when he was stopped by the police. The car he was driving turned out to have been involved in a shooting, and he was arrested. Eventually a court sentenced him to six years in prison. This might have been an uneventful case, had it not been for a piece of technology that had aided the judge in making the decision. They used COMPAS, an algorithm that determines the risk of a defendant becoming a recidivist.

One crucial challenge of real-world multilingual speech recognition is the long-tailed distribution problem, where some resource-rich languages like English have abundant training data, but a long tail of low-resource languages have varying amounts of limited training data. To overcome the long-tail problem, in this paper, we propose Adapt-and-Adjust (A2), a transformer-based multi-task learning framework for end-to-end multilingual speech recognition. The A2 framework overcomes the long-tail problem via three techniques: (1) exploiting a pretrained multilingual language model (mBERT) to improve the performance of low-resource languages; (2) proposing dual adapters consisting of both language-specific and language-agnostic adaptation with minimal additional parameters; and (3) overcoming the class imbalance, either by imposing class priors in the loss during training or adjusting the logits of the softmax output during inference. Extensive experiments on the CommonVoice corpus show that A2 significantly outperforms conventional approaches.

Deep neural networks are often not robust to semantically-irrelevant changes in the input. In this work we address the issue of robustness of state-of-the-art deep convolutional neural networks (CNNs) against commonly occurring distortions in the input such as photometric changes, or the addition of blur and noise. These changes in the input are often accounted for during training in the form of data augmentation. We have two major contributions: First, we propose a new regularization loss called feature-map augmentation (FMA) loss which can be used during finetuning to make a model robust to several distortions in the input. Second, we propose a new combined augmentations (CA) finetuning strategy, that results in a single model that is robust to several augmentation types at the same time in a data-efficient manner. We use the CA strategy to improve an existing state-of-the-art method called stability training (ST). Using CA, on an image classification task with distorted images, we achieve an accuracy improvement of on average 8.94% with FMA and 8.86% with ST absolute on CIFAR-10 and 8.04% with FMA and 8.27% with ST absolute on ImageNet, compared to 1.98% and 2.12%, respectively, with the well known data augmentation method, while keeping the clean baseline performance.

As an enterprise discipline, data science is the antithesis of Artificial Intelligence. The one is an unrestrained field in which creativity, innovation, and efficacy are the only limitations; the other is bound by innumerable restrictions regarding engineering, governance, regulations, and the proverbial bottom line. Nevertheless, the tangible business value praised by enterprise applications of AI is almost always spawned from data science. The ModelOps trend spearheading today's cognitive computing has a vital, distinctive correlation within the realm of data scientists. Whereas ModelOps is centered on solidifying operational consistency for all forms of AI--from its knowledge base to its statistical base--data science is the tacit force underpinning this motion by expanding the sorts of data involved in these undertakings.

In this study, we propose a multicriteria group decision making (MCGDM) algorithm under uncertainty where data is collected as intervals. The proposed MCGDM algorithm aggregates the data, determines the optimal weights for criteria and ranks alternatives with no further input. The intervals give flexibility to experts in assessing alternatives against criteria and provide an opportunity to gain maximum information. We also propose a novel method to aggregate expert judgements using cloud models. We introduce an experimental approach to check the validity of the aggregation method. After that, we use the aggregation method for an MCGDM problem. Here, we find the optimal weights for each criterion by proposing a bilevel optimisation model. Then, we extend the technique for order of preference by similarity to ideal solution (TOPSIS) for data based on cloud models to prioritise alternatives. As a result, the algorithm can gain information from decision makers with different levels of uncertainty and examine alternatives with no more information from decision-makers. The proposed MCGDM algorithm is implemented on a case study of a cybersecurity problem to illustrate its feasibility and effectiveness. The results verify the robustness and validity of the proposed MCGDM using sensitivity analysis and comparison with other existing algorithms.

Cooperative Intelligent Transportation Systems (C-ITS) will change the modes of road safety and traffic management, especially at intersections without traffic lights, namely unsignalized intersections. Existing researches focus on vehicle control within a small area around an unsignalized intersection. In this paper, we expand the control domain to a large area with multiple intersections. In particular, we propose a Multi-intersection Vehicular Cooperative Control (MiVeCC) to enable cooperation among vehicles in a large area with multiple unsignalized intersections. Firstly, a vehicular end-edge-cloud computing framework is proposed to facilitate end-edge-cloud vertical cooperation and horizontal cooperation among vehicles. Then, the vehicular cooperative control problems in the cloud and edge layers are formulated as Markov Decision Process (MDP) and solved by two-stage reinforcement learning. Furthermore, to deal with high-density traffic, vehicle selection methods are proposed to reduce the state space and accelerate algorithm convergence without performance degradation. A multi-intersection simulation platform is developed to evaluate the proposed scheme. Simulation results show that the proposed MiVeCC can improve travel efficiency at multiple intersections by up to 4.59 times without collision compared with existing methods.

We introduce federated marginal personalization (FMP), a novel method for continuously updating personalized neural network language models (NNLMs) on private devices using federated learning (FL). Instead of fine-tuning the parameters of NNLMs on personal data, FMP regularly estimates global and personalized marginal distributions of words, and adjusts the probabilities from NNLMs by an adaptation factor that is specific to each word. Our presented approach can overcome the limitations of federated fine-tuning and efficiently learn personalized NNLMs on devices. We study the application of FMP on second-pass ASR rescoring tasks. Experiments on two speech evaluation datasets show modest word error rate (WER) reductions. We also demonstrate that FMP could offer reasonable privacy with only a negligible cost in speech recognition accuracy.

Amazon Transcribe is an automatic speech recognition (ASR) service that makes it easy to add speech-to-text capabilities to your applications. Today, we're excited to launch Japanese, Korean, and Brazilian Portuguese language support for Amazon Transcribe streaming. To deliver streaming transcriptions with low latency for these languages, we're also announcing availability of Amazon Transcribe streaming in the Asia Pacific (Seoul), Asia Pacific (Tokyo), and South America (São Paulo) Regions. Amazon Transcribe added support for Italian and German languages earlier in November 2020, and this launch continues to expand the service's streaming footprint. Now you can automatically generate live streaming transcriptions for a diverse set of use cases within your contact centers and media production workflows.

Back when the world seemed bright and ambitious--another century, it might have been--I managed to convince myself, despite a lot of evidence to the contrary, that what I really needed in my life was an assistant. This was December, the month when traditionally I can no longer outrun the clerical tasks that have stalked me since the middle of the year. I had weeks of crinkled receipts to expense: the year-end tax on negligence. I was halfway through the process of contesting the charge on a vaccine shot that my insurance company had refused to cover, and I had to transcribe hours of interviews before I could begin to write--the only use of my time which generates an income. As a moonless night wore on, filled with snacking and monsters, I futzed with the formulas in my sad expense spreadsheets and knew that these were hours of life I'd never get back.

Non-Intrusive Load Monitoring (NILM) is a computational technique to estimate the power loads' appliance-by-appliance from the whole consumption measured by a single meter. In this paper, we propose a conditional density estimation model, based on deep neural networks, that joins a Conditional Variational Autoencoder with a Conditional Invertible Normalizing Flow model to estimate the individual appliance's power demand. The resulting model is called Prior Flow Variational Autoencoder or, for simplicity PFVAE. Thus, instead of having one model per appliance, the resulting model is responsible for estimating the power demand, appliance-by-appliance, at once. We train and evaluate our proposed model in a publicly available dataset composed of power demand measures from a poultry feed factory located in Brazil. The proposed model's quality is evaluated by comparing the obtained normalized disaggregation error (NDE) and signal aggregated error (SAE) with the previous work values on the same dataset. Our proposal achieves highly competitive results, and for six of the eight machines belonging to the dataset, we observe consistent improvements that go from 28% up to 81% in NDE and from 27% up to 86% in SAE.