The current iPhone upgrade to iOS 13.2 brings a variety of features, not the least of which is improved privacy for those who use Siri. Responding to the outcry over how it handles the data collected by its voice assistant, Apple has offered users a way to delete all of the recordings that Siri collects during use. The company has also stopped sharing audio recordings with human staffers in order to improve its service. Instead, it asks you to opt in to that feature via a pop-up that appears when you upgrade to this latest version of its mobile operating system. If you were too quick to opt in when you upgraded and have decided you don't want to share your voice with Apple (or if you opted out and have decided that you don't mind if a few Apple employees listen to your voice), you can easily change your mind. In addition, you can now ask Apple to delete all of your audio information from Siri (which used to be a very convoluted and unsure process).

Get great prices on the things you actually want. 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. In my opinion, there couldn't be anything more exciting than waking up to a great deal on a product you actually want. And this morning, I woke up to several on Amazon.

On the heels of several new acquisitions and product announcements in recent months, Motorola Solutions is announcing a new radio equipped with a voice assistant, which the company says is the first of its kind. The public safety radio is called APX NEXT, building upon the company's prior APX two-way radios, and the virtual assistant that controls it has been dubbed ViQi (pronounced "Vicky"). The company's news release on Thursday said the radio is FirstNet-ready, built with LTE connectivity, and is the first APX radio to feature a touchscreen, designed for field use including with rain or gloves. Motorola Solutions Chief Technology Officer Mahesh Saptharishi said that besides being able to control the radio, the virtual assistant responds to commands like "ViQi, run a license plate," and can also look up driver's license information and vehicle identification numbers. He said other functions will come with future updates.

In the battle of the buds, our "taste test" was striking. A friend and I both compared listening to the Foo Fighters "Learn to Fly" on Amazon's new Echo Buds and the product it aims to emulate, what Apple calls the best-selling headphone "in the world," the AirPods. The Amazon product "sounded tinnier," said Jan Schreiber, a Laguna Beach, California-based photographer. The AirPods had richer bass and a fuller sound. We switched to other songs, and the verdict didn't change.

Tinder, the most popular dating app in the world, has banned teens under the age of 18 but it's not stopping them from signing up. A jilted Australian doctor pleaded guilty Monday to sending 9,000 abusive and threatening messages to her former Tinder date, according to a new report. Radiologist Denise Jane Lee, 40, of Sydney, copped to four of 10 charges against her ahead of a scheduled five-day hearing in the Downing Centre Local Court, the Australian Associated Press reported. Lee, who was arrested in February 2017, copped to three counts of using a carriage service to harass, menace or offend and one count of intimidation, according to the report. Six additional charges were withdrawn.

AI will grow into a $118.6 billion industry by 2025. That isn't something you should take lightly. AI has become an integral part of our everyday lives. When we ask Alexa to play our favorite song, use Google Maps to find our way to a new Chinese restaurant, or even use portrait mode to take pictures of our friends – we're adopting AI without even realizing it. Indeed, the way we carry out generic tasks has shifted far beyond our imagination since the rise of AI.

Digital agencies today are brimming with ideas that can help brands integrate with voice-enabled technology. For Niraj Ruparel, National Head- Mobile, Mindshare India, conversational commerce using voice skill technology in India means serious business. In conversation with exchange4media, he delves into the nuances of voice technology, how brands can ensure that voice interaction for users is a seamless experience and what is working in the favour of Voice as the next big digital trend. The agency's tryst with voice began in January this year, explains Ruparel after global giants Google and Amazon recognised the potential for voice in India. "Voice is pretty big in Tier 2 markets, which is in terms of the penetration or how we reach out to audiences in the rural market. If you talk about the ecosystem per se, we're talking about close to 100 crore active sim cards in India and almost 450 million sim cards are resting on feature phones where the only mode of communication is Voice, so that plays a dominant role there. But now we see those 550 million SIMs which are sitting on 400 million smartphones, 30 per cent of those people have now started querying on Voice Assistants."

Science fiction is quickly becoming everyday reality. Chatbots, robots, digital assistants, automated vehicles, virtual assistants, and much more... are the products of artificial intelligence (AI), which is already transforming entire industries. An infographic by TechJury, provider of one-step tech guides and product reviews, provides a detailed overview of AI. The infographic begins with a timeline of AI, starting in the mid-20th century with the "father of theoretical computer science and artificial intelligence," Alan Turing, who developed the "Turing test" for determining what qualifies as artificial intelligence. The infographic goes on to outline various classifications of AI, provides examples of AI technology, highlights statistics about the AI market, and lists the companies and countries at the forefront of the AI race.

Many mobile applications and virtual conversational agents now aim to recognize and adapt to emotions. To enable this, data are transmitted from users' devices and stored on central servers. Y et, these data contain sensitive information that could be used by mobile applications without user's consent or, maliciously, by an eavesdropping adversary. In this work, we show how multimodal representations trained for a primary task, here emotion recognition, can unintentionally leak demographic information, which could override a selected opt-out option by the user. We analyze how this leakage differs in representations obtained from textual, acoustic, and multimodal data. We use an adversarial learning paradigm to unlearn the private information present in a representation and investigate the effect of varying the strength of the adversarial component on the primary task and on the privacy metric, defined here as the inability of an attacker to predict specific demographic information. We evaluate this paradigm on multiple datasets and show that we can improve the privacy metric while not significantly impacting the performance on the primary task. To the best of our knowledge, this is the first work to analyze how the privacy metric differs across modalities and how multiple privacy concerns can be tackled while still maintaining performance on emotion recognition.

Matrix completion is often applied to data with entries missing not at random (MNAR). For example, consider a recommendation system where users tend to only reveal ratings for items they like. In this case, a matrix completion method that relies on entries being revealed at uniformly sampled row and column indices can yield overly optimistic predictions of unseen user ratings. Recently, various papers have shown that we can reduce this bias in MNAR matrix completion if we know the probabilities of different matrix entries being missing. These probabilities are typically modeled using logistic regression or naive Bayes, which make strong assumptions and lack guarantees on the accuracy of the estimated probabilities. In this paper, we suggest a simple approach to estimating these probabilities that avoids these shortcomings. Our approach follows from the observation that missingness patterns in real data often exhibit low nuclear norm structure. We can then estimate the missingness probabilities by feeding the (always fully-observed) binary matrix specifying which entries are revealed or missing to an existing nuclear-norm-constrained matrix completion algorithm by Davenport et al. [2014]. Thus, we tackle MNAR matrix completion by solving a different matrix completion problem first that recovers missingness probabilities. We establish finite-sample error bounds for how accurate these probability estimates are and how well these estimates debias standard matrix completion losses for the original matrix to be completed. Our experiments show that the proposed debiasing strategy can improve a variety of existing matrix completion algorithms, and achieves downstream matrix completion accuracy at least as good as logistic regression and naive Bayes debiasing baselines that require additional auxiliary information.