Lifeboat Foundation

We all become accustomed to the tone and pattern of human speech at an early age, and any deviations from what we have come to accept as “normal” are immediately recognizable. That’s why it has been so difficult to develop text-to-speech (TTS) that sounds authentically human. Google’s DeepMind AI research arm has turned its machine learning model on the problem, and the resulting “WaveNet” platform has produced some amazing (and slightly creepy) results.

Google and other companies have made huge advances in making human speech understandable by machines, but making the reply sound realistic has proven more challenging. Most TTS systems are based on so-called concatenative technologies. This relies upon a database of speech fragments that are combined to form words. This tends to sound rather uneven and has odd inflections. There is also some work being done on parametric TTS, which uses a data model to generate words, but this sounds even less natural.

DeepMind is changing the way speech synthesis is handled by directly modeling the raw waveform of human speech. The very high-level approach of WaveNet means that it can conceivably generate any kind of speech or even music. Listen above for an example of WaveNet’s voice synthesis. There’s an almost uncanny valley quality to it.

Continue reading “Google’s DeepMind develops creepy, ultra-realistic human speech synthesis” »

Tune In, Take Control.

With OV, your day becomes more productive, enjoyable, and just a whole lot easier. Use your voice to play a song, order groceries and check the news. Switch seamlessly between the best music and calls, voice commands and real world conversations, without missing a beat and without touching your phone.

“The big-screen cinema company said Thursday that it and several partner companies created a $50 million investment fund focused on virtual reality media projects like films and video games.”

Read more

“The fairy tale will be made available for free on Daydream, Google’s mobile virtual reality product.”

Read more

To make it easier to sift through data on proteins, a composer and a biologist turned them into music, an approach that could have many applications.

“After being spurned in Chicago, Lucas’s Museum of Narrative Art is looking for a West Coast home.”

Read more

“Christophe Szpajdel, a Belgian designer who has crafted more than 7,000 logos for bands since the 1980s, explains that, just like any other form of design, a good metal logo relies on basic principles like symmetry, visual harmony, letter height, and precision.”

Read more

Microcomputers are great for learning about code and hardware. The VoCore2 Mini is the smallest ever, packing full Linux functionality and wireless connectivity into a coin-sized device. New Atlas Deals has it for just $42.99.

This impressive little computer is capable of running programs in C, Java, Ruby, JavaScript, and many other languages. This means you can code the VoCore2 to expand its functionality, turning it into a VPN gateway, airplay music station, and much more.

You can also augment the VoCore2 with hardware components for further tinkering fun. Add a USB webcam to turn it into a home security camera, attach a microphone to issue voice commands to Siri or Echo, and so on. Your projects are limited only by your imagination.

“AT&T and Time Warner are reportedly in talks about a potential merger.”

Read more