Toggle light / dark theme

Meta AI researchers have moved a step forward in the field of generative AI for speech with the development of Voicebox. Unlike previous models, Voicebox can generalize to speech-generation tasks that it was not specifically trained for, demonstrating state-of-the-art performance.

Voicebox is a versatile generative system for speech that can produce high-quality audio clips in a wide variety of styles. It can create outputs from scratch or modify existing samples. The model supports speech synthesis in six languages, as well as noise removal, content editing, style conversion, and diverse sample generation.

Traditionally, generative AI models for speech required specific training for each task using carefully prepared training data. However, Voicebox adopts a new approach called Flow Matching, which surpasses diffusion models in performance. It outperforms existing state-of-the-art models like VALL-E for English text-to-speech tasks, achieving better word error rates (5.9% vs. 1.9%) and audio similarity (0.580 vs. 0.681), while also being up to 20 times faster. In cross-lingual style transfer, Voicebox surpasses YourTTS by reducing word error rates from 10.9% to 5.2% and improving audio similarity from 0.335 to 0.481.

[Prof. Marvin Minsky] is a very well-known figure in the field of computing, having co-founded the MIT AI lab, published extensively on AI and computational intelligence, and, let’s not forget, inventing the confocal microscope and, of course, the useless machine. But did you know he also was a co-developer of the first Logo “turtle,” and developed a computer intended to run Logo applications in an educational environment? After dredging some PDP-10 tapes owned by the MIT Media Lab, the original schematics for his machine, the Turtle Terminal TT2500 (a reference to the target price of $2500, in 1970 terms), are now available for you to examine.

The machine itself was created in an interesting way; by affixing discrete socketed TTL chips to a large panel, some three hundred or so, the interconnect was performed automatically using a computer-controlled wiring machine that read the design from magnetic tape. The 2,500 used 16-bit user-definable instructions read from a tiny 4k control store. Instruction microcode was read from a 1k microcode store backed up with 64k of RAM. Unusually, it sported a dual display configuration, with one text display and a second vector display for rendering real-time graphics. The machine was intended to run the Logo programming language developed by [Seymour Papert] and others, but this was impossible due to its tiny control store. Instead, it became a display terminal for a connected computer with sufficient resources. You can read more about this fascinating period of time in AI, the life of [Minsky], and others in this New Yorker article.

[Lars Brinkhoff] has created a simulation of the TT2500 running atop a PDP11/45 emulator, a demo of which can be seen below. What a fun story! We covered the passing of the great man back in 2016, which is well worth another read, we reckon. If you want to relive the useless machine, we’ve seen them ranging from the simple to the complex.

Cuneiform is the oldest known form of writing, but it is so difficult to read that only a few hundred experts around the world can decode the clay tablets filled with wedge-shaped symbols. Now, a team of archaeologists and computer scientists from Israel has created an AI-powered translation program for ancient Akkadian cuneiform, allowing tens of thousands of already digitized tablets to be translated into English instantaneously.

Globally, libraries, museums, and universities have more than half a million clay tablets inscribed with cuneiform. But the sheer number of texts, and the tiny number of Akkadian readers — a language no one has spoken or written for 2,000 years — means just a small fraction of these tablets have been translated.

A new Google Translate-type program may allow armchair archaeologists to try their hand at cuneiform interpretation.

Frequent flyers rejoice, as a team of Swiss researchers have crafted a foldable flat robot, capable of rotating itself into nearly any shape one can imagine, fitting easily under any airplane seat or overhead cabin. The robot, whose design was inspired by the decorative flair of Japanese origami, is able to pack itself completely flat like a piece of Ikea furniture, according to a recent write-up in Futurism. With other recent developments in science and robotics leading to incredible advancements, such as liquid robots that can phase through metal bars like a T-1000, as well as a host of robotic enhancements courtesy of Boston Dynamics, many people are beginning to fear that science has gone too far.

It is essential to carefully consider the advantages and disadvantages of AI as its integration into various aspects of society continues to evolve. Proactive measures are necessary to maximise the benefits of AI while mitigating potential drawbacks. A research study conducted by the American Psychological Association reveals that employees who frequently engage with artificial intelligence (AI) systems are more likely to experience loneliness, leading to insomnia and increased after-work drinking, reported scitechdaily. The study was carried out across various countries, including the United States, Taiwan, Indonesia, and Malaysia, with consistent findings across different cultures.

The dangers of isolation

Lead researcher Pok Man Tang, PhD, who previously worked in an investment bank utilising AI systems, was inspired to investigate this timely issue.

Researchers have used a machine learning model to identify three compounds that could combat aging. They say their approach could be an effective way of identifying new drugs, especially for complex diseases.

Cell division is necessary for our body to grow and for tissues to renew themselves. Cellular senescence describes the phenomenon where cells permanently stop dividing but remain in the body, causing tissue damage and aging across body organs and systems.

Ordinarily, senescent cells are cleared from the body by our immune system. But, as we age, our immune system is less effective at clearing out these cells and their number increases. An increase in senescent cells has been associated with diseases such as cancer, Alzheimer’s disease and the hallmarks of aging such as worsening eyesight and reduced mobility. Given the potentially deleterious effects on the body, there has been a push to develop effective senolytics, compounds that clear out senescent cells.