Google DeepMind claims to have significantly improved computer-generated speech with its AI technology, paving the way forward for sophisticated talking machines like those seen in sci-fi films like „Her" and „Ex-Machina."

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.

In 2014 Google bought a UK-based artificial intelligence research lab called DeepMind for a hefty 530 million. Since then, DeepMind has made rapid progress in AI technologies, including health and gaming applications. The latest achievement of DeepMind is WaveNet, an AI computer program that can almost mimic the way humans speak. Experts say that WaveNet has "halved" the gap between machine-speak and a natural human voice. So what we're talking about here is more like Jarvis from Iron Man than Arnold Schwarzenegger in Terminator – or any of his other movies, for that matter!

The DeepMind unit, which Google bought in 2014 for roughly 533 million, develops supercomputers and artificial intelligence (AI). One of the AI programs DeepMind has developed is Wavenet, designed to mimic human speech. In blind tests human listeners indicated that Wavenet was the most natural sounding text-to-speech (TTS) program, after hearing samples from different programs in English and Mandarin Chinese. TTS programs continue to struggle to sound like natural speech, and Wavenet, while increasingly similar, does not yet sound just like actual human speech. Wavenet simulates certain brain functions by using what in artificial intelligence is called a "neural network."

Google's DeepMind AI is learning how to talk. And learning how to do it like a person, not a computer. DeepMind has many learning projects going on right now, but the newest one to catch our ears seems to be an increasingly realistic voice and speech pattern system that eliminates more and more of the inhuman, robotic patterns we use to identify computers. Imagine if Siri, Cortana, or Alexa started having inflection, variances, and realistic breathing patterns. Instead of sounding like this, it might sound like this.

Google's secretive British DeepMind division is teaching its AI to talk like a human. The groundbreaking project has already halved the quality gap between computer systems and human speech, its creator say. Called WaveNet, it is capable of creating natural-sounding synthesized speech by analyzing sound waves from the human voice - rather than focusing on the human language. Google's DeepMind claims to have an AI that produces more natural-sounding synthesized speech. Google acquired UK-based DeepMind in 2014 for 533 million, and it has since beat a professional human Go player, learned how to play the Atari game Space Invaders and has read through thousands of Daily Mail and CNN articles.

Researchers at Google's DeepMind artificial intelligence division claim to have come up with a way of producing much more natural-sounding synthesized speech, compared with the techniques that are currently in use. Existing text-to-speech (TTS) systems tend to use a system called concatenative TTS, where the audio is generated by recombining fragments of recorded speech. There's also a technique called parametric TTS that generates speech by passing information through a vocoder, but that sounds even less natural. So DeepMind has come up with a new technique called WaveNet that learns from the audio it's fed, and produces raw audio sample-by-sample. To give an idea of how detailed that is, we're talking at least 16,000 samples per second.

Google's DeepMind unit, which is working to develop super-intelligent computers, has created a system for machine-generated speech that it says outperforms existing technology by 50 percent. U.K.-based DeepMind, which Google acquired for about 400 million pounds ( 533 million) in 2014, developed an artificial intelligence called WaveNet that can mimic human speech by learning how to form the individual sound waves a human voice creates, it said in a blog post Friday. In blind tests for U.S. English and Mandarin Chinese, human listeners found WaveNet-generated speech sounded more natural than that created with any of Google's existing text-to-speech programs, which are based on different technologies. WaveNet still underperformed recordings of actual human speech. Many computer-generated speech programs work by using a large data set of short recordings of a single human speaker and then combining these speech fragments to form new words.

Google's DeepMind unit, which is working to develop super-intelligent computers, has created a system for machine-generated speech that it says outperforms existing technology by 50 percent. U.K.-based DeepMind, which Google acquired for about 400 million pounds ( 533 million) in 2014, developed an artificial intelligence called WaveNet that can mimic human speech by learning how to form the individual sound waves a human voice creates, it said in a blog post Friday. In blind tests for U.S. English and Mandarin Chinese, human listeners found WaveNet-generated speech sounded more natural than that created with any of Google's existing text-to-speech programs, which are based on different technologies. WaveNet still underperformed recordings of actual human speech. Many computer-generated speech programs work by using a large data set of short recordings of a single human speaker and then combining these speech fragments to form new words.