Virtual assistants have been taught to catch thoughts on the fly.

logo11d 4 1

Virtual assistants have been taught to catch thoughts on the fly.

The bottleneck in building automation systems is not design and installation, but management.

Design and installation are carried out by specialists.

There is no need to teach them, they themselves know what to connect to what and where the signal comes from.

And all these miracles of technology have to be managed by the average person, for whom remote controls and menus cause fear and horror.

Now, if I just said it, and it worked as it should, then everything would be much simpler with the arrival of automation in our homes.

But it means that soon control panels will become a thing of the past, like cassette recorders.

This is confirmed by an article by Olga Baklitskaya-Kameneva on the website vokrugsveta.ru

Virtual assistants have been taught to catch thoughts on the fly.

“It’s not our business to produce gadgets, we only create new technologies,” Professor Wolfgang Walster, head of the German Research Center for Artificial Intelligence (DFKI, Das Deutsche Forschungszentrum für Künstliche Intelligenz), modestly said about the achievements of his colleagues to European journalists. (Wolfgang Wahlster).

However, these “gadgets” themselves were also presented to journalists: a store of the future, a “smart” apartment and car, and new generation computer games. All these are the latest joint developments of DFKI and the Institute of Informatics of the Society. Max Planck (Max-Planck-Institut für Informatik) with partners who are taking Germany to the forefront in the field of computer science.

Both institutes are located on the premises of the University of Saarbrücken (Universität des Saarlandes), which allows its scientists to develop new solutions, implement them in programs, and collaborate with professionals from other fields — physicists, chemists, biologists, linguists and psychologists. And if the Institute of Informatics deals mainly with fundamental research, the DFKI focuses on their application in specific technical devices.

Talk to your tech

Imagine you are rushing to the office by car, making your way through the crowded streets of an awakened city and dreaming of starting your working day with a Queen song, and your favorite one at that. You don’t even have to take your hands off the wheel, just clearly say to the minicomputer: “Play “I’m Going Slightly Mad” for me!” and the music will start playing. And if the song is not in your CD collection, the computer will quickly retrieve it from the World Wide Web. Not bad?

Modern MP3 players can store a huge amount of data, but the user interfaces that actually guide the consumer through the information jungle are limited. Scientists from DFKI offer their development for communicating with technology called “BabbleTunes”. It’s a multilingual, mixed-input system that processes voice commands almost instantly and allows you to control all the basic functions of your MP3 player (with the touch screen also available, of course).

We watched how it all works on a demo BMW. The developers suggested that the system prepare a selection of songs by European rock bands from the Internet, then play the one that was written last year. The system responded almost instantly.

To develop new user interfaces that significantly simplify human communication with technology, with DFKI. In July 2008, a special company SemVox GmbH was created. Its main purpose is to give users the ability to choose whether to communicate with it by giving orders by voice or by gesturing, using a keyboard, a mouse, or a combination of the above.

The point of the technology used is to extract the technical details of the content from the multimodal flow of information. This technology can help transform your living room into an interactive infotainment center. “You can safely go out in the evening by instructing the TV before going out: “Record me the latest episode of The Simpsons in the evening,” interactive interface developer Jochen Steigner, one of the four founders of SemVox, explained to us its advantages in everyday life.

Virtual poker

The speech synthesis system, which is also capable of conveying emotions, can be seen in action in a virtual casino: there you will be offered to play poker with computer characters — Sam and Max.

You receive 52 poker cards, which differ from ordinary ones in having built-in chips — RFID tags. RFID technology allows you to identify an object using radio signals.

It is interesting to observe how during the game, depending on the development of the situation, the emotional state of virtual players changes; they comment on the development of the game in different ways in synthetic voices, and, like real players, sometimes bluff.

This is one of the achievements of the IDEAS4Games project, which is being carried out by DFKI with colleagues from Berlin and Augsburg. It opens up new possibilities for the next generation of computer games. The main component of IDEAS4Games is the author’s development in the field of artificial intelligence SceneMaker, on the basis of which interactive applications are created.

In order to emphasize the expressiveness of virtual characters in a computer game, the developers used the latest speech synthesis system methods and advanced emotion modeling. In combination with the author’s developments, a good result is obtained — flexible dialogue and improved reactions of virtual characters.

The speech synthesis structure was based on the MARY (Modular Architecture for Research on speech sYnthesis) system, originally developed by researchers from the DFKI Language Technology lab in collaboration with the Institute of Phonetics of the University of Saarbrücken, and to convey the emotional mood of virtual For characters, scientists used the ALMA (A Layered Model of Affect) computer model.

Players’ emotions and moods are calculated in real time based on game events and in accordance with 34 poker rules.

“Our goal is to create virtual characters who can fully participate in a conversation with the user, that is, react not only to the content of phrases, but also to the interlocutor’s facial expression, timbre and intonation of voice, behavior, and, in the end, able to figure out when a person smiles, and when he is angry.

To do this, together with our European colleagues, we are developing a system of “attentive artificial listener” (SAL, Sensitive Artificial Listener) within the framework of the project “sustained emotionally colored human-machine dialogue using non-verbal means of expression” (SEMAINE, Sustained Emotionally colored Machine-human Interaction using Nonverbal Expression). We are already close to teaching a computer to conduct a normal conversation,” says project participant Marc Schröder.

Flying over Google Earth

“Would you like to fly to Moscow from Saarbrücken in a couple of minutes, straight to your home and right now?” — the nice guys ask at the Google Earth screen. Matthieu Deru and Simon Bergweiler from the Advanced Tangible Interface Lab (AdvanTI-Lab) at DFKI are champions of watching the institute’s videos on Youtube.

The young researchers used one of the latest developments from the Nintendo gaming company, designed for fitness and video games — the so-called Wii Balance Board gaming controller.

An inexpensive, easy-to-use input device is a small platform with built-in motion sensors. They track how a person changes his position — leaning forward, backward, right or left — and transmit it to a computer on which special software is installed.

You stand on the board, look at the screen with a Google Earth map and, changing the position of your body (like an avid surfer), head towards your home, flying over Europe. By pressing the buttons, you can change the flight altitude. And a fan of computer games wearing stereo glasses in front of a hemispherical screen will feel like a participant in a virtual plot.

It should be noted that not only museums and authors of computer games showed great interest in the brilliant development of scientists. In hospitals, the device can be used for the rehabilitation of patients with vestibular disorders. “We have no doubt that many scientists will follow our example, pick up and develop our ideas,” the guys are sure.

Beethoven and billions of bytes: a search service in the world of music

Forgot the name of the song that has been spinning in your head since the morning? Or the author of the melody that was played? Whistle or sing it to the computer, and it will give you everything it “knows”: the author, the title, all the performers of the works that are in its music database. This amazing search system is being developed by Meinard Müller, a senior researcher at the Institute of Informatics.

How to find the desired music discs in the database based on a few bars — a small audio fragment? Is it possible to compare different performances of a piece of music and synchronize them in time? How to automatically process the structure of a piece of music on a computer? These questions are of interest to both music lovers and professional musicians.

“Mathematics gives us the necessary tools to develop ways to solve these problems and use them for specific melodies. “I am helped in this by our previous research in the group of Michael Clausen from the University of Bonn in the field of audio signal processing, the theory of algorithmic representations, algebraic complexity theory and Fourier transforms,” says Müller. German conservatories became interested in unusual developments — a good help in classes on musical literature.

Store of the future

A “smart” grocery cart will help you select the desired product from the list you have compiled, guide you to the desired shelf and display all the information about the purchase.

The digital sommelier will tell you about the flavor bouquet and the intricacies of the production of alcoholic beverages, compare wine from different vintages and advise which dish is best to serve it with. Store refrigerators will store information about the “history” of products, tell you when they were in the store, how long they can be stored and under what conditions.

And the products themselves can tell a lot about themselves: where and when they were made, in what warehouse they were stored, in what combination they are especially tasty, for what range of products there is a discount. And, of course, you will have a virtual assistant at your disposal who will explain which products you may be allergic to and which contain GMOs, preservatives and dyes.

You will soon be able to take advantage of these innovations in the stores of the German retail chain GLOBUS SB. In cooperation with its representatives, the Trade Innovation Laboratory (IRL, Innovative Retail Laboratory) was created at DFKI. Scientists, together with trade professionals, are working on several projects for the store of the future, which will be located on an area of ​​five hundred square meters.

Of course, such a store needs a lot of different electronics — touch screens, RFID tags on products and in the floor (for navigation), antennas on shelves, temperature sensors… But the main thing is specialized software.

Our acquaintance with “computer science” in German ended for us in the famous Dagstuhl Castle or Leibniz Center for Informatics (Schloss Dagstuhl — Leibniz-Zentrum für Informatik GmbH), which is called the Mecca of computer science: every month there are held international conferences, and the names of all those invited to the castle are entered in the “Dagstuhl Book”.

“We and our European colleagues have taken the lead in this field because our research allows us to create technologies that work today,” Professor Reinhard Wilhelm assured me at parting, showing me the sights of the famous castle, of which he is the scientific director.

Добавить комментарий

18 − пять =

Мы используем cookie-файлы для наилучшего представления нашего сайта. Продолжая использовать этот сайт, вы соглашаетесь с использованием cookie-файлов.
Принять