Deep-learning artificial intelligence is helping grapple with plenty of problems in the modern world. But it also has its part to play in helping solve some ancient problems as well — such as assisting in the translation of 2,500-year-old clay tablet documents from Persia’s Achaemenid Empire.

These tablets, which were discovered in modern-day Iran in 1933, have been studied by scholars for decades. However, they’ve found the translation process for the tablets — which number in the tens of thousands — to be laborious and prone to errors. A.I. technology can help.

“We have initial experiments applying machine learning to identify which cuneiform symbols are present in images of a tablet,” Sanjay Krishnan, assistant professor at the University of Chicago’s Department of Computer Science, told Digital Trends. “Machine learning works by extrapolating patterns from human-labeled examples, and this allows us to automate the annotations in the future. We envision that it is a step toward significant automation in the analysis and study of these tablets.”

In this case, the human-labeled examples are annotated tablets from the Persepolis Fortification Archive’s (PFA) Online Cultural and Historical Research Environment (OCHRE) dataset. In DeepScribe, a collaboration between researchers from the University of Chicago’s Oriental Institute and its Department of Computer Science, they used a training set of more than 6,000 annotated images to build a neural network able to read unanalyzed tablets in the collection.

When the algorithm was tested on other tablets, it was able to translate the cuneiform signs with an accuracy level of around 80%. The hope is to increase this benchmark in the future. Even if that doesn’t happen, though, the system could be used to translate large amounts of the tablets, leaving human scholars to focus their efforts on the really difficult bits.

“Cuneiform is a script used since the third millennium BCE to write multiple languages including Sumerian, Akkadian, and Elbaite,” Susanne Paulus, associate professor for Assyriology, told Digital Trends.

Cuneiform poses a series of particular challenges for machine translation. Firstly, it was written by impressing a reed stylus into wet clay. This makes cuneiform one of very few three-dimensional script systems. Secondly, cuneiform is a complex script system using hundreds of signs. Each sign has different meanings depending on its context. Thirdly, cuneiform tablets are ancient artifacts. They are often broken and hard to decipher, which means reading one tablet can take days.

“So far, we have an initial prototype that suggests that such techniques are very effective in a controlled setting,” Krishnan said. “Given a clean image of a single symbol, [we can] determine what the symbol is. Our next step is to develop more robust models that account for context and data quality.”

The post Deep-learning A.I. is helping archaeologists translate ancient tablets appeared first on Artificial Intelligence.

Washington – A new artificial intelligence tool can create realistic videos from audio files alone. This technology, developed at the University of Washington, has been tested on speeches made by former President Obama.

The technology is based on newly prepared algorithms, which are designed to overcome a limitation with ‘computer vision’. This is with turning audio clips into realistic, lip-synced videos of the person who is speaking the words. The developed algorithms learn from videos that exist “in the wild”, such as on the Internet or elsewhere.

To do so involved training a neural network (a collection of connected units called artificial neurons) to view videos of an individual and then to translate different audio sounds into basic mouth shapes. The second area was using a new mouth synthesis technique to realistically superimpose mouth shapes and textures onto an existing reference video of a given person.

Individual brain cells within a neural network are highlighted in this image obtained by CMU’s Sandra Kuhlman using a fluorescent imaging technique

Carnegie Mellon University

To test out the technology, the research group generated a realistic video of Barack Obama discussing such diverse subjects as terrorism, fatherhood and employment. The video was created using audio clips alone together with a separate video image of the former president. The video overcomes a major problem with adding audio to video, where the mouth of the speaker appears unrealistic.

Discussing the outcome, lead researcher Professor Ira Kemelmacher- Shlizerman enthused: “These type of results have never been shown before.” To this required an artificial intelligence algorithm, one capable of learning and anticipating the intricate patterns of human speech. The reason Obama was chosen for the project was due to the sheer volume of available recordings.

President Barack Obama addresses citizens at a town hall meeting in Santa Monica, California, October 9, 2014

White House

The technology will be presented to the August meeting of SIGGRAPH 2017. A white paper has been produced titled “Synthesizing Obama: Learning Lip Sync from Audio”, to discuss the technology.

What does technology this offer businesses?

The advantages to businesses are considerable, allowing high quality audit recordings to be made and later turned into videos of a higher resolution that would be possible using a standard camera and with taking archival sound recordings, which is an area that may appeal to the entertainments industry. Imagine, for example, being able to hold a conversation with a historical figure in virtual reality by creating visuals just from audio.

What could this mean for you?

For consumers, video chat tools like Skype, Google Hangouts or Messenger will enable any person to collect videos that could be used to train computer models. A further appeal to businesses is since streaming audio over the Internet requires much less bandwidth than video, the new software will put an end to video chats that ‘time out’ as a result of poor connections. This is by reversing the process , that is feeding video into the network instead of just audio. Often with ‘video chats’ the audio is good but the video is poor, which is something that frustrates many business professionals and hampers attempts by businesses to reduce the number of meetings by ‘going digital’.

The post Artificial intelligence tool turns audio into video appeared first on Artificial Intelligence.