A convent turned hotel, Caribou Coffee, and progressive coworking space called The Coven--plus more things to see and do while on a business trip to Minneapolis and St. Paul. All products featured on WIRED are independently selected by our editors. However, we may receive compensation from retailers and/or from purchases of products through these links. Minnesota is the birthplace of the supercomputer, developed for code cracking during World War II. Tech giants of their day, including Cray Research and Control Data Corporation, were based in the Twin Cities.

"Alexa," I asked the Echo display in my kitchen, "what was that song from The Hills? You know, that MTV show? Can you play it on the Echo Show in the office?" The old Alexa wouldn't have had a prayer of answering such a poorly worded query. But the new Alexa, now packing AI-enhanced smarts, handled it easily.

Did you know that soundtrack concerts are among the most popular for touring orchestras? A full third of the Royal Philharmonic Orchestra's first-time audience members are coming to the concert hall via their favourite series and movies – and video games. It is a huge cultural growth area, and one that may have gone unrecognised by the general public. "It is impossible to ignore video game music now," says Tommy Pearson, founder and artistic director of the inaugural London Soundtrack festival. "The sheer creativity and artistry in games is incredible, and it's been fascinating to see so many composers blossom in the genre."

The field of text privatization often leverages the notion of $\textit{Differential Privacy}$ (DP) to provide formal guarantees in the rewriting or obfuscation of sensitive textual data. A common and nearly ubiquitous form of DP application necessitates the addition of calibrated noise to vector representations of text, either at the data- or model-level, which is governed by the privacy parameter $\varepsilon$. However, noise addition almost undoubtedly leads to considerable utility loss, thereby highlighting one major drawback of DP in NLP. In this work, we introduce a new sentence infilling privatization technique, and we use this method to explore the effect of noise in DP text rewriting. We empirically demonstrate that non-DP privatization techniques excel in utility preservation and can find an acceptable empirical privacy-utility trade-off, yet cannot outperform DP methods in empirical privacy protections. Our results highlight the significant impact of noise in current DP rewriting mechanisms, leading to a discussion of the merits and challenges of DP in NLP, as well as the opportunities that non-DP methods present.

Music source separation demixes a piece of music into its individual sound sources (vocals, percussion, melodic instruments, etc.), a task with no simple mathematical solution. It requires deep learning methods involving training on large datasets of isolated music stems. The most commonly available datasets are made from commercial Western music, limiting the models' applications to non-Western genres like Carnatic music. Carnatic music is a live tradition, with the available multi-track recordings containing overlapping sounds and bleeds between the sources. This poses a challenge to commercially available source separation models like Spleeter and Hybrid Demucs. In this work, we introduce 'Sanidha', the first open-source novel dataset for Carnatic music, offering studio-quality, multi-track recordings with minimal to no overlap or bleed. Along with the audio files, we provide high-definition videos of the artists' performances. Additionally, we fine-tuned Spleeter, one of the most commonly used source separation models, on our dataset and observed improved SDR performance compared to fine-tuning on a pre-existing Carnatic multi-track dataset. The outputs of the fine-tuned model with 'Sanidha' are evaluated through a listening study.

The increasing demand for mental health services has highlighted the need for innovative solutions, particularly in the realm of psychological conversational AI, where the availability of sensitive data is scarce. In this work, we explored the development of a system tailored for mental health support with a novel approach to psychological assessment based on explainable emotional profiles in combination with empathetic conversational models, offering a promising tool for augmenting traditional care, particularly where immediate expertise is unavailable. Our work can be divided into two main parts, intrinsecaly connected to each other. First, we present RACLETTE, a conversational system that demonstrates superior emotional accuracy compared to state-of-the-art benchmarks in both understanding users' emotional states and generating empathetic responses during conversations, while progressively building an emotional profile of the user through their interactions. Second, we show how the emotional profiles of a user can be used as interpretable markers for mental health assessment. These profiles can be compared with characteristic emotional patterns associated with different mental disorders, providing a novel approach to preliminary screening and support.

The Grammy award-winning star discusses what he thinks about when he is picking which songs to record. Keith Urban has had his fair share of strange interactions with fans. When asked about his wildest moment with a fan during his recent appearance on "The Kelly Clarkson Show," the 57-year-old country singer recalled the time a fan threw an unexpected item on stage for him to sign. "I was playing a show, and this girl yells out from the audience, 'will you sign my leg?'" Urban explained. "And I went, 'of course' what a great moment. This was years, a long, long time ago. She's out there, I say yep come on up! Then she disappears, I couldn't see her. Then she pops up out of the same spot and throws this prosthetic leg up on stage!"

Countless flowing green wigs risked spontaneous combustion on a 36-degree Melbourne evening as thousands of J-pop fans queued outside John Cain Arena on Friday night. But the heat was irrelevant to the night's headline pop attraction, Hatsune Miku. Miku, as she's known to fans, is a 157cm-tall avatar of a teenage girl with green pigtails. She represents a digital bank of vocal samples created by the ominous-sounding Crypton Future Media using Yamaha's Vocaloid voice synthesiser technology. Users input lyrics and melodies which are "sung" by the bank's sampled voice (Hatsune Miku is voiced by the actor Saki Fujita); some Vocaloid producers "tune" the software to be especially convincing, while others embrace its artificiality.

This year marks the 30th anniversary of the Warcraft gaming universe but there's not going to be a BlizzCon gathering to celebrate it. So Blizzard is doing the next-best thing by holding a live streaming event. Blizzard announced that its special Warcraft 30th Anniversary Direct stream will start at 1PM ET on Wednesday, November 13. The broadcast will run on Blizzard's official streaming channels for Twitch, YouTube and TikTok. There aren't many details available about what Warcraft fans can expect to see during the livestream except for a special concert celebrating World of Warcraft's 20th anniversary.

As a big soundtrack fan, I love any occasion in which musicians perform them live in concert. So, I'm excited that Sony has created PlayStation The Concert, a world tour featuring the scores from titles like The Last of Us, God of War, Ghost of Tsushima and Horizon. Previous video game concerts have included The Legend of Zelda: Symphony of the Goddesses, which ran from 2012 to 2017. The announcement coincides with the 30th anniversary of PlayStation, with the production meant to reflect "30 years of making games that have not only captivated players but are celebrated for their breathtaking and immersive soundtracks too," Sid Shuman, senior director of Sony Interactive Entertainment Content Communications, stated in the release. The tour will start on April 15, 2025 in Dublin before traveling to cities around Europe like Paris, Oslo, London and Budapest.