Teresa Carey: This is Scientific American's 60-Second Science. Every morning at five o'clock, composer Walter Werzowa would sit down at his computer to anticipate a particular daily e-mail. It came from six time zones away, where a team had been working all night (or day, rather) to draft Beethoven's unfinished 10th Symphony--almost two centuries after his death. The e-mail contained hundreds of variations, and Werzowa listened to them all. Carey: Werzowa was listening for the perfect tune--a sound that was unmistakably Beethoven.

Recent advances in visually-induced audio generation are based on sampling short, low-fidelity, and one-class sounds. Moreover, sampling 1 second of audio from the state-of-the-art model takes minutes on a high-end GPU. In this work, we propose a single model capable of generating visually relevant, high-fidelity sounds prompted with a set of frames from open-domain videos in less time than it takes to play it on a single GPU. We train a transformer to sample a new spectrogram from the pre-trained spectrogram codebook given the set of video features. The codebook is obtained using a variant of VQGAN trained to produce a compact sampling space with a novel spectrogram-based perceptual loss. The generated spectrogram is transformed into a waveform using a window-based GAN that significantly speeds up generation. Considering the lack of metrics for automatic evaluation of generated spectrograms, we also build a family of metrics called FID and MKL. These metrics are based on a novel sound classifier, called Melception, and designed to evaluate the fidelity and relevance of open-domain samples. Both qualitative and quantitative studies are conducted on small- and large-scale datasets to evaluate the fidelity and relevance of generated samples. We also compare our model to the state-of-the-art and observe a substantial improvement in quality, size, and computation time. Code, demo, and samples: v-iashin.github.io/SpecVQGAN

Amazon is the Standard Oil of the 21st century. Its business operations and global reach dwarf those of virtually every other company on the planet -- and exceed the GDP of more than a few countries -- illustrating the vital importance innovation has on the modern economy. In his latest book, The Exponential Age: How Accelerating Technology is Transforming Business, Politics and Society, author Azeem Azhar examines how the ever-increasing pace of technological progress is impacting, influencing -- and often rebuilding -- our social, political and economic mores from the ground up. Excerpted from The Exponential Age: How Accelerating Technology is Transforming Business, Politics and Society by Azeem Azhar. In 2020, Amazon turned twenty-six years old.

The seas were blessedly calm as we sailed across the channel and straight up the Seine, into the heart of Francia. The skald led us in song, our voices booming across the placid waters, thundering in our veins. We leaped from our longboat onto the shores of Francia, shouting glory to the All-Father as we charged up the beaches. The sounds of glorious battle filled the air. Squelch, squelch, squish, grunt, clang, yell, grunt, clang, squish, squish, squidge.

While music genre plays an enormous role in building and displaying social identity, the emotional expression of a song and -- even more importantly -- its emotional impression on the listener is often underestimated in the domain of music preferences. Only a few decades back, choosing music by genre and/or artist was effectively the only option. Want to hear live music? Well, choose an artist or a -- typically genre-based -- festival. Alright, check out our CD shelves categorized by genre and pick an album by an artist you like.

AI stem separation tool for precise stem extraction. Kanye West has recently dropped the Donda Stem Player, a portable speaker to remix, customize tracks and isolate stems from audio. Initially, the speaker was designed as a creative way to interact with Kanye's new album, but it turns out that it's a creators tool on its own. The idea is to mix and match different songs and parts from the new Kanye's album and listen to new tracks each time you press play. You can also upload your own tracks to the Stem Player.

The uncanny valley is the abrupt dip in human affinity to a non-human creature when we see it approaching human-like characteristics. For instance, the spooky feeling when one looks at Sofia the robot or Lil Miquela the Instagram influencer. Really though, Lil Miquela gives me the creeps when I go through her timeline. It is the eeriness of a realistic face with personalized captions with her sense of awareness that she is not a real person that is quite unsettling. There is something surreal about it that makes working with it exciting.

Thales has launched Season 3 of AI@Centech, a business accelerator designed to help artificial-intelligence focused startups tackle real-world problems. Thales selected five international startups in early August out of a pool of more than 200 potential competitors from around the world. The search for qualified startups began in February when the program published challenges ranging from how to more efficiently use AI to manage satellites to applying augmented cognition to improve human decision-making. The selected startups will work closely with Thales business coaches and AI experts who will advise them on critical skills such as fundraising, product enhancement, design, visibility, proof-of-concept, and market access. Season 3 of AI@Centech follows last year's successful second season of the program, which resulted in many achievements such as Thales and MyDataModels winning a bid with the municipality of Nice Côte d'Azur, France for underwater threat detection.

1Artificial Intelligence and International Economic Law: A Research and Policy Agenda. Shin-yi Peng, Ching-Fu Lin, and Thomas Streinz.

When he died in 1827 aged 56, Ludwig van Beethoven left his 10th symphony unfinished. Only a few handwritten notes briefly detailing his plans for the piece have survived, with most just being incomplete ideas or fragments of themes or melodies. Now, a multidisciplinary team of computer scientists at Rutgers University-based start-up Playform AI have trained an artificial intelligence to mimic the great composer's style and used it to write a complete symphony based on these initial sketches. We spoke to the lead researcher on the project, Professor Ahmed Elgammal, to find out more. Beethoven left sketches in different forms, mainly musical sketches, but also some written notes with some ideas in as well.