Microsoft continues AI push with expanded Bot Framework, new Cognitive Services

microsoft build 2017 cognitive bot framework harry shum
During the Build 2017 keynote on Wednesday, Harry Shum, executive vice president of  Microsoft’s Artificial Intelligence and Research Group, detailed the company’s plans to bring artificial intelligence into the hands of every developer. This initiative includes making enhancements to the Microsoft Bot Framework, adding new AI-based “cognitive” services and a new “lab” for testing experimental cognitive services, incorporating artificial intelligence into additional products and services, and more.

For starters, Microsoft’s Cognitive Services suite brings machine-based intelligence spanning vision, speech, language, knowledge, and search to applications. They’re the backbone of features like facial recognition, speech recognition, text translation, image search, and so on. Microsoft now provides 29 distinct Cognitive Services, with Bing Custom Search, Custom Vision Service, Custom Decision Service, and Video Indexer added to the portfolio Wednesday.

microsoft build 2017 cognitive bot framework custom vision service

Cornelia Carapcea, Microsoft senior product manager, came on stage to demonstrate Custom Vision Service. This enables developers to create their own custom artificial intelligence models across speech, language, text, and image understanding. To create a model, developers merely bring their training data (a dozen photographs, for example), click a button to train the model in minutes, and then create the final model to be used in applications.

In the onstage demo, Carapcea used a smartphone app to recognize a just-plucked plant in a photograph taken by the device. She pointed out that the recognition aspect feature didn’t require deep learning, thousands of training images, and a wait time of “hours” as the model learned that specific plant.

Prior to the demo, she uploaded around 24 images of that specific plant to a photo album stored on the Custom Vision Service platform. She also had loads of other plants uploaded, and she eventually clicked on a big green “train” button to create what she called an “end point” that would be used by the mobile app to recognize a variety of plants.

She said that once a model is created, “active learning” kicks in to analyze all additional images taken by users of the app. This feature will hold on to all images that best define the plant visually, and then present those selected images to the developer along with a “confidence” percentage. The developer clicks on each questionable image to save it as a stored reference and then retrains the model, thus making it “smarter.”

To see this feature in action, head over to Microsoft’s dedicated Custom Vision site.

microsoft build 2017 cognitive bot framework starship commander

In another demo demonstrating the power of Microsoft’s Cognitive Services platform, creative director Alexander Mejia of Human Interact talked about a pre-alpha build of Starship Commander, a choose-your-own virtual reality adventure narrative. The game uses natural language processing enabling players to have “real” verbal conversations with the in-game characters. What’s cool about this aspect is that the studio created custom words based on the game’s science-fiction theme, which isn’t possible using off-the-shelf voice recognition software.

One of the services used in the Starship Commander backend is Language Understanding Intelligent Service (LUIS), which enabled Human Interact to create the custom language model. The game also relies on Custom Speech Service so that it understands all the sci-fi lingo spoken by the players.

“With LUIS, you basically give it a couple of statements,” Mejia said. “You crunch it, you start typing in your own statements, and it’s shockingly scary how good it picks up, even stuff you didn’t put in there.”

Microsoft also launched the Cognitive Services Labs platform, enabling developers to play with experimental cognitive services. One of the first experiments on the plate is a gesture API that enables end users to control and interact with apps using simple hand motions. Shum indicated more experiments are coming.

“The improvements we are making in understanding speech and language are driving a paradigm shift — moving away from a world where we’ve had to understand computers to one where computers understand humans. We call this conversational AI,” Shum said in press release.

In addition to new Cognitive Services, the company announced expansions to the Microsoft Bot Framework, a platform for creating intelligent “robots” within apps and services. Since the platform’s launch in 2016, more than 130,000 developers have signed on, and now Microsoft is enhancing the platform with “Adaptive Cards” that can be used across multiple apps and platforms.

“Developers also can now publish to new channels including Skype for Business, Bing and Cortana, and implement Microsoft’s payment request API for fast and easy checkout with their bots,” Shum added.

Microsoft also injected its Azure cloud platform with a service called Batch AI Training, which enables developers to train their own deep neural networks using any framework they choose, such as Microsoft Cognitive Toolkit, TensorFlow, and Caffe. Developers can create their environment and run these models against multiple processors, multiple graphics chips, and “eventually” field-programmable gate arrays (FPGAs), which are integrated circuits that can be configured by developers.

microsoft build 2017 cognitive bot framework translator powerpoint

Finally, Microsoft announced a new Office feature called Presentation Translator. Available in PowerPoint, it uses the company’s AI capabilities to translate PowerPoint presentations between multiple languages in real time. Attendees of a meeting can use a link generated by Presentation Generator to see the translation on their device. It joins PowerPoint Designer and Office Researcher, two previous features that used the company’s AI knowledge.

According to Yina Arenas, Microsoft principal program manager, the Presentation Translator add-in relies on the Custom Speech Service and Translator Speech API services offered on Microsoft’s Cognitive Services platform. To demonstrate the new add-in’s use, she went into PowerPoint and clicked on the “Start Subtitles” button. A pop-up menu appeared that allowed her to choose the language she would verbally use in the presentation (Spanish), and the language she wanted to use in the subtitles (English). She also chose where the subtitles would reside in the presentation.

Now here’s the kicker. Shum downloaded the Microsoft Translator app to an iPhone, scanned a barcode on the PC’s screen (users can also enter a unique conversation code), and then chose his native language — Mandarin Chinese. After that, Arenas moved on to demonstrate the real-time translation across multiple devices.

“Artificial intelligence can eliminate the linguistic barriers between the presents,” Arenas said aloud in Spanish. Meanwhile on the PC monitor, her words appeared in English while they also appeared in Chinese on Shum’s iPhone. After that, she unmuted the presentation, allowing Shum to verbally make a statement in Chinese through the iPhone’s built-in microphone. The statement appeared on the PC monitor in English.

“The PowerPoint Translator add-in custom-trains the model based on my voice and my slides using the power of the Custom Speech Service,” Arenas said.

Overall, these changes don’t have much immediate impact on consumers. However, Microsoft hopes that its Cognitive Services and Bot Framework will allow the design of next-generation applications that use AI to interact more intuitively with users. Only time can reveal the wisdom in this approach, but the company’s continued commitment in these areas, which were first detailed in-depth during last year’s Build conference, shows the company expects big things from these technically complex initiatives.

Updated 5-10-2017 by Kevin Parrish to reflect three onstage demos.

Emerging Tech

Awesome Tech You Can’t Buy Yet: heat-powered watches, phone cases with reflexes

Check out our roundup of the best new crowdfunding projects and product announcements that hit the web this week. You may not be able to buy this stuff yet, but it sure is fun to gawk!
Emerging Tech

Face-scanning A.I. can help doctors spot unusual genetic disorders

Facial recognition can unlock your phone. Could it also be used to identify whether a person has a rare genetic disorder, based on their facial features? New research suggests it can.
Mobile

Rumors suggest Apple will release an iPhone XR successor this year

While it's not been long since the last iPhones launched, rumors for the next iPhone are already surfacing. Apple's 2019 flagship could include a variety of upgrades ranging from a new design to enhanced features.
Computing

Rollable keyboard, couch potato’s dream headline top mice and keyboards at CES

New mice and keyboards may not offer much in the way of performance enhancements for your PC, but they are lovely to use and look gorgeous. Here's a list of our favorites from CES 2019.
Deals

From Air to Pro, here are the best MacBook deals for January 2019

If you’re in the market for a new Apple laptop, let us make your work a little easier: We hunted down the best up-to-date MacBook deals available online right now from various retailers.
Computing

Change your mouse cursor in Windows with these quick tips

The standard mouse cursor is boring, so change it! With this guide on how to change your mouse cursor in Windows, you can choose to use one of Microsoft's pre-installed cursors or download something a bit more extravagant.
Computing

Go hands-free in Windows 10 with speech-to-text support

Looking for the dictation, speech-to-text, and voice control options in Windows 10? Here's how to set up Speech Recognition in Windows 10 and use it to go hands-free in a variety of different tasks and applications within Windows.
Computing

Printing to PDF in Windows is easy, no matter which method you use

Microsoft's latest operating system makes it easier than ever to print to PDF in Windows, but there are alternative methods for doing so, even if you want to forgo Adobe Acrobat. Here's how.
Computing

Changing a PDF into an EPUB file is easier than you might think

If you like to read on a tablet or ebook reader, you'll find that ePUB files offer a number of advantages over PDFs. With this guide, we'll show you how to convert a PDF to EPUB in a few quick steps.
Computing

Need to combine a PDF? Here's how to get it done on both Windows and Mac

Sometimes juggling multiple files at once is more of a hassle than a convenience, especially when a single file would do. This quick guide will teach you how to combine PDF files on Windows, MacOS, or with online tools.
Computing

Don’t even bother with the rest. Here are the only laptop brands that matter

If you want to buy your next laptop based around a specific brand, it helps to know which the best brands of laptops are. This list will give you a good grounding in the most reliable, quality laptop manufacturers today.
Computing

Secure your Excel documents with a password by following these quick steps

Excel documents are used by people and businesses all over the world. Given how often they contain sensitive information, it makes sense to keep them from the wrong eyes. Thankfully, it's easy to secure them with a password.
Computing

Style up your MacBook Air with one of these great cases or sleeves

Whether you’re looking for added protection or a stylish flourish, you’re in the right place for the best MacBook Air cases. We have form-hugging cases, luxurious covers and padded sleeves priced from $10 to $130. Happy shopping!
Computing

Getting Windows 10 updated doesn't have to be so painful

Windows update not working? It's a more common problem than you might think. Fortunately, there are a few steps you can take to troubleshoot it and in this guide we'll break them down for you step by step.