Listen to New Google AI Program Talk Like a Human and Write Music
Google's DeepMind creates AI that blows away existing speech synthesizers.
Google-owned artificial intelligence company DeepMind presented a deep neural network that generates amazingly human-like speech. Called WaveNet, this AI makes a significant advancement over existing speech synthesizers. What’s more, it can write pretty good classical music.
DeepMind is a British company, previously known for creating machine-learning AI software that beat the world champion of the notoriously-intricate game Go. Machine learning allows computer systems to teach themselves and make predictions based on gathered data.
The company claims that its WaveNet creates speech that can mimic any human voice and closes the gap with human speech performance by more than 50%. Google’s 500-person blind test study found people rating WaveNet’s English speech at a 4.21 (5 being realistic human speech), while concatenate speech got a 3.86 and parametric an even worse 3.67.
WaveNet also generated speech in Mandarin, which got similar results.
They did this by re-imagining currently used text-to-speech (TTS) processes. The two most common being concatenative TTS, used by Apple’s Siri, which involves pre-recorded fragments of speech, and parametric TTS, which sounds even less natural, getting speech generated through computer algorithms.
What’s different about WaveNet is that its can directly model the raw waveform of an audio signal, an extremely complicated task that required a novel neural network. WaveNet learns from voice recordings, then on its own creates speech. This independence also allows the program to generate other kinds of audio, like music.
To bolster their claim, DeepMind released some samples, comparing their WaveNets with samples made by concatenate and parametric TTS. You be the judge.
And now, this is what WaveNet generated:
After it was trained on a dataset of classical piano music, WaveNet produced these intriguing musical creations of its own:
What are the implications of this new tech? While it also means our eventual robotic overlords should being easier to talk to, virtual AI assistants like Siri or Cortana could benefit sooner. Google isn’t promising this is headed straight to such applications, however, as WaveNet requires serious computing power.
This achievement shows again the potential of DeepMind's neural networks which can and are being used for fraud and spam detection, handwriting recognition, image search, translation and other tasks.
In a very Google move, the paper on WaveNet is available on Google Drive here.
Want to know more about DeepMind? Check out this video:
Lumina Foundation is partnering with Big Think to unearth the next large-scale, rapid innovation in post-high school education. Enter the competition here!
Soon, parents may be able to prescribe music to their kids to help them focus.
- Instead of prescribing medications to kids with ADD or ADHD, Clark and his team at Brain.fm are looking to music as another option for treatment.
- Through a grant from the National Science Foundation, the company is developing music that features "neural-phase locking" — a combination of different principles that create specific characteristics in the brain, such as increased concentration or relaxation.
- As long as they're listening to the music, the neural phase-locking aspect of Brain.fm's tunes has the potential to keep people focused.
There are four main stages. Each has its own particular set of advancements and challenges.
Don't you wish you could predict your child's behavior with 100 percent accuracy? Any realistic parent knows it's an impossible daydream, but an appealing one nonetheless. Kids will always surprise you. There are so many factors that go into behavior, not to mention the fact that internal and external forces can sometimes make kids act out of character.
"I should be as happy as I'm ever going to be right now, but I'm not. Is this it?"
SMARTER FASTER trademarks owned by The Big Think, Inc. All rights reserved.