In the last couple of years, deep learning techniques have transformed the world of artificial intelligence. One by one, the abilities and techniques that humans once imagined were uniquely our own have begun to fall to the onslaught of ever more powerful machines. Deep neural networks are now better than humans at tasks such as face recognition and object recognition. They've mastered the ancient game of Go and thrashed the best human players. But there is a problem.

Artificial intelligence and machine learning are at the core of the concept of a self-driving vehicle. By definition, such an automobile should not need human input, and must learn how to deal with the things it will face on a daily basis while driving on the open road. Powerful node hardware, sophisticated AI programming and a large, reliable backend are necessary for such an operation. Those same tools, however, could be used in a different sort of machine learning. Deep learning is a type of AI that seeks to imitate the human mind, and is found in projects like Google's Deep Dream.

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."

IBM has unveiled a series of new servers, that have been designed to help propel cognitive workloads and drive greater data center efficiency. Featuring a new chip, the three Linux-based servers incorporate innovations from the OpenPOWER community and are a part of the Power Systems LC lineup, that IBM claims, delivers higher levels of performance and greater computing efficiency than the x86-based server. The servers clam to have been co-developed with global technology companies and the new Power Systems are uniquely designed to propel artificial intelligence, deep learning, high performance data analytics and other compute-heavy workloads to help businesses and cloud service providers save data center costs. According to Big Blue, the three new systems are an expansion of its Linux server portfolio comprised of a specialized line of servers co-developed with fellow members of the OpenPOWER Foundation. The new servers join the Power Systems LC lineup that IBM states, is designed to outperform x86-based servers on a variety of data-intensive workloads.

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. The system, known as WaveNet, is able to generate human speech by forming individual sound waves that are used in a human voice. Additionally, because it is designed to mimic human brain function, WaveNet is capable of learni... Artist Ai Weiwei poses next to images of Andy Warhol at the Museum of Modern Art in 1987.

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.

The system, known as WaveNet, is able to generate human speech by forming individual sound waves that are used in a human voice. Additionally, because it is designed to mimic human brain function, WaveNet is capable of learning from extremely detailed -- at least 16,000 samples per second -- audio samples. The program statistically chooses which samples to use and pieces them together, producing raw audio. While most of the existing TTS systems also use the same "piece by piece" idea, they largely utilize concatenative TTS. Despite drawing from a large database, these systems are restricted to combinations of short recorded speech fragments from a single speaker, which makes modifying the voice or its inflection difficult.

If you want to talk about something important or sensitive, odds are that conversation will happen over the phone rather than email or text. The sound of someone's voice is an important part of trusting them--but the ability to trust the voice on the other end of that call is human might change. Google DeepMind announced a new speech generation method it calls WaveNet, which could bring artificial intelligence closer than ever to indiscernibly mimicking human speech. The algorithm can easily learn different voices and even generates artificial breaths, according to a DeepMind blog post. DeepMind, the London-based AI firm acquired by Google in 2014, broadly works to "solve intelligence," a goal that spans health, data center energy efficiency, and ancient Chinese board games.

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." The London-based research lab, acquired by Google in 2014 for a reported 400 million, announced on Thursday that it has developed a talking computer programme called "WaveNet" that halves the quality gap that currently exists between human speech and computer speech. Although WaveNet sounds more like a human voice than existing artificial voice generators -- known as "text-to-speech" (TTS) systems -- it requires too much computing power to make it practical, meaning Google won't be integrating it into its products any time soon, according to The Financial Times. Aäron van den Oord, a research scientist, at DeepMind said: "Mimicking realistic speech has always been a major challenge, with state-of-the-art systems, composed of a complicated and long pipeline of modules, still lagging behind real human speech. Our research shows that not only can neural networks learn how to generate speech, but they can already close the gap with human performance by over 50%.

Generating speech from a piece of text is a common and important task undertaken by computers, but it's pretty rare that the result could be mistaken for ordinary speech. A new technique from researchers at Alphabet's DeepMind takes a completely different approach, producing speech and even music that sounds eerily like the real thing. Early systems used a large library of the parts of speech (phonemes and morphemes) and a large ruleset that described all the ways letters combined to produce those sounds. The pieces were joined, or concatenated, creating functional speech synthesis that can handle most words, albeit with unconvincing cadence and tone. WaveNet, as the system is called, takes things deeper.