We present a deep learning method for singing voice conversion. The proposed network is not conditioned on the text or on the notes, and it directly converts the audio of one singer to the voice of another. Training is performed without any form of supervision: no lyrics or any kind of phonetic features, no notes, and no matching samples between singers. The proposed network employs a single CNN encoder for all singers, a single WaveNet decoder, and a classifier that enforces the latent representation to be singer-agnostic. Each singer is represented by one embedding vector, which the decoder is conditioned on. In order to deal with relatively small datasets, we propose a new data augmentation scheme, as well as new training losses and protocols that are based on backtranslation. Our evaluation presents evidence that the conversion produces natural signing voices that are highly recognizable as the target singer.

If you make a purchase by clicking one of our links, we may earn a small share of the revenue. However, our picks and opinions are independent from USA Today's newsroom and any business incentives. Nothing gets me more excited for the weekend than finding a good deal on Amazon. Not only am I saving money, but with Prime shipping, I can have it on my doorstep on Saturday or Sunday--which is even more reason to celebrate. There are hundreds of deals to choose from, which makes it a little more tricky to decide if things are actually a good deal and not just a bad product at a good price or a good product at a not-so-great price.

Is workplace surveillance about improving productivity or simply a way to control staff and weed out poor performers? Courtney Hagen Ford, 34, left her job working as a bank teller because she found the surveillance she was under was "dehumanising". Her employer logged her keystrokes and used software to monitor how many of the customers she helped went on to take out loans and fee-paying accounts. "The sales pressure was relentless," she recalls. She decided selling fast food would be better, but ironically, left the bank to do a doctorate in surveillance technology.

In this paper, we consider advancing web-scale knowledge extraction and alignment by integrating OpenIE extractions in the form of (subject, predicate, object) triples with Knowledge Bases (KB). Traditional techniques from universal schema and from schema mapping fall in two extremes: either they perform instance-level inference relying on embedding for (subject, object) pairs, thus cannot handle pairs absent in any existing triples; or they perform predicate-level mapping and completely ignore background evidence from individual entities, thus cannot achieve satisfying quality. We propose OpenKI to handle sparsity of OpenIE extractions by performing instance-level inference: for each entity, we encode the rich information in its neighborhood in both KB and OpenIE extractions, and leverage this information in relation inference by exploring different methods of aggregation and attention. In order to handle unseen entities, our model is designed without creating entity-specific parameters. Extensive experiments show that this method not only significantly improves state-of-the-art for conventional OpenIE extractions like ReVerb, but also boosts the performance on OpenIE from semi-structured data, where new entity pairs are abundant and data are fairly sparse.

With the wide deployment of machine learning (ML) based systems for a variety of applications including medical, military, automotive, genomic, as well as multimedia and social networking, there is great potential for damage from adversarial learning (AL) attacks. In this paper, we provide a contemporary survey of AL, focused particularly on defenses against attacks on statistical classifiers. After introducing relevant terminology and the goals and range of possible knowledge of both attackers and defenders, we survey recent work on test-time evasion (TTE), data poisoning (DP), and reverse engineering (RE) attacks and particularly defenses against same. In so doing, we distinguish robust classification from anomaly detection (AD), unsupervised from supervised, and statistical hypothesis-based defenses from ones that do not have an explicit null (no attack) hypothesis; we identify the hyperparameters a particular method requires, its computational complexity, as well as the performance measures on which it was evaluated and the obtained quality. We then dig deeper, providing novel insights that challenge conventional AL wisdom and that target unresolved issues, including: 1) robust classification versus AD as a defense strategy; 2) the belief that attack success increases with attack strength, which ignores susceptibility to AD; 3) small perturbations for test-time evasion attacks: a fallacy or a requirement?; 4) validity of the universal assumption that a TTE attacker knows the ground-truth class for the example to be attacked; 5) black, grey, or white box attacks as the standard for defense evaluation; 6) susceptibility of query-based RE to an AD defense. We then present benchmark comparisons of several defenses against TTE, RE, and backdoor DP attacks on images. The paper concludes with a discussion of future work.

Buying the right monitor for your PC is crucial, especially if you spend many hours in front of it either because you work from home or you're an avid gamer. It's not as simple as just spending more to get more, though. Different monitors are better suited to different tasks so knowing which one is right for you is just as important. There are four main considerations: size, panel type, refresh rate and resolution. If you only use your PC occasionally then you can get away with a modestly sized screen: say, 20-24 inches.

T-Mobile hasn't been quick to fulfill its promises of launching TV service, but it finally has something to show following all the early hype: it's launching TVision Home, a rebranded and retuned version of Layer3's broadband-based IPTV service. It's not the fully independent streaming service you might have hoped for (that's coming later in 2019). However, the telecom is hoping to bring a dash of its straightforward "Uncarrier" strategy to the TV world -- provided you're willing to pay. To start, T-Mobile is bringing its no-shock billing to TV. You'll pay $100 per month ($90 if you're also a phone customer) for 150-plus channels and $10 per connected TV, but there are no hidden fees used to jack up the real price.

Camera model identification refers to the problem of linking a picture to the camera model used to shoot it. As this might be an enabling factor in different forensic applications to single out possible suspects (e.g., detecting the author of child abuse or terrorist propaganda material), many accurate camera model attribution methods have been developed in the literature. One of their main drawbacks, however, is the typical closed-set assumption of the problem. This means that an investigated photograph is always assigned to one camera model within a set of known ones present during investigation, i.e., training time, and the fact that the picture can come from a completely unrelated camera model during actual testing is usually ignored. Under realistic conditions, it is not possible to assume that every picture under analysis belongs to one of the available camera models. To deal with this issue, in this paper, we present the first in-depth study on the possibility of solving the camera model identification problem in open-set scenarios. Given a photograph, we aim at detecting whether it comes from one of the known camera models of interest or from an unknown device. We compare different feature extraction algorithms and classifiers specially targeting open-set recognition. We also evaluate possible open-set training protocols that can be applied along with any open-set classifier. More specifically, we evaluate one training protocol targeted for open-set classifiers with deep features. We observe that a simpler version of those training protocols works with similar results to the one that requires extra data, which can be useful in many applications in which deep features are employed. Thorough testing on independent datasets shows that it is possible to leverage a recently proposed convolutional neural network as feature extractor paired with a properly trained open-set classifier...

When it comes to artificial intelligence and machine learning, how journalists view the technology, and how willing they are to delve into the many layers it can empower, is the secret sauce in creating a better workplace. Five journalists from The Wall Street Journal, Washington Post, WIRED, Dogtown Media and Graphika visited with more than 1,000 students across the Missouri School of Journalism, the Trulaske College of Business, the College of Engineering and the College of Arts and Science, March 18-19, as part of the Reynolds Journalism Institute's Innovation Series. Artificial intelligence and machine learning are already transforming news operations in ways unimaginable even several months ago, much of it transformative and positive. Among the changes AI is helping implement: Customized content, improved reader/viewer/listener/user relationships, moderating and policing comment sections, and creating more efficient workflows. For journalists, the key is in embracing change and using a generalist's approach to understanding a rapidly and vastly changing ecosystem that has already begun transforming newsrooms across the globe.

The Hugo Awards are some of the most important prizes in genre fiction, including science fiction and fantasy. Among past winners we see Ursula K. Le Guin, Isaac Asimov, Neil Gaiman, and most recently, N.K. Jemisin, who made history for winning Best Novel three years in a row for every book in her Broken Earth series. This year, nestled among nominees for novels, short stories, and even individual episodes of The Good Place and Doctor Who, is an unexpected contender for the Best Related Work category: the primarily women-run fan fiction website Archive of Our Own. Archive of Our Own (often known as "AO3" for short) is an online platform for fan works-- creative work based on existing media like novels, books, and video games, produced by fans of the originals. The nearly 5 million works archived there--4,690,000 as of this writing--represent almost 2 million registered users and countless more who visit the site every day, consuming content and leaving comments.