The trolleys will leave the hotel and CMU on the following schedule:

Hotel	CMU	Hotel	Notes
6:30	6:45	7:00	Group A
6:45	7:00	7:15	Group B
7:00	7:15	7:30	If you want to leave at this time, you will have to wait until 7:30 to join group C
7:15	7:30	7:45	Group C
7:30	7:45	8:00	Group D
7:45	8:00	8:15
8:00	8:15	8:30
8:15	8:30	8:45
8:30	8:45	9:00
8:45	9:00	9:15
9:00	9:15	9:30	Last Pickup

People will tour the 2 main demo areas with a guide. You will have free time in the Atrium, where refreshments and sandwiches will be served. Some small demos will take place in the Atrium.

Please note the trolleys hold a maximun of 30 occupants. The driver may request to see you nametag. You should plan on staying an hour and a half on campus before returning to the Renaissance hotel. If you are staying somewhere between CMU and the Renaissance hotel (Oakland area), you can ask the driver to drop you off on the way.

In Interactive Systems Lab NHS 2602

NESPOLE! is a speech-to-speech machine translation research system designed to provide fully functional speech-to-speech capabilities within real-world settings of common users involved in e-commerce applications. The project is funded jointly by the European Commission and the US NSF.  The NESPOLE! system uses a client-server architecture to allow a common user, who is browsing web-pages on the internet, to connect seamlessly in real-time to an agent of the service provider, using a video-conferencing channel and with speech-to-speech translation services mediating the conversation. Shared web pages and annotated images supported via a Whiteboard application are available to enhance the communication.

Gaze/Face Tracking:
Gaze information plays an important role in identifying a person's focus of attention. The information can provide useful communication cues to a multimodal interface. For example, it can be used to identify where a person is looking, and what he/she is paying attention to.
A person's gaze direction is determined by two factors: the orientation of the head, and the orientation of the eyes.

The sign translation will demonstrate a PDA-based sign system which can detect, recognize and translate signs. In this system we embed multi-resolution, adaptive search in a hierarchical framework with different emphases at each layer. We also introduce an intensity-based OCR method to recognize character in various fonts and lighting condition, where we use Gabor transform to obtain local features, and LDA for selection and classification of features. The recognition rate is 92.4% for the testing set got from the natural sign. Sign is different from the normal used sentence. It is short, with many abbreviations and place's names. Here we briefly introduce a rule-based place name translation. We have integrated all these functions in a PDA, which can capture sign image, auto segment and recognize the Chinese sign, and translate it into English.

top

Brad Myers’s Lab NSH 2613

Peebles: We will be demonstrating a variety of applications we have createdthat allow small handheld Personal Digital Assistants (PDAs) such asPalm organizers or Pocket PC / Windows CE devices, to be usefuladjuncts to "fixed" computers. With today's wireless technologies,such as BlueTooth and IEEE 802.11, connecting handhelds andconventional computers is no longer an occasional event forsynchronization. Instead, the devices are frequently in close,interactive communication. We will be demonstrating a variety of applications created as part of the Pebbles project which are related to the following two ICMI'02 papers: B. Myers, et. al., "Flexi-modal and Multi-Machine User Interfaces", and J. Nichols, et. al., "Requirements for Automatically Generating Multi-Modal Interfaces for Complex Appliances".
See http://www.cs.cmu.edu/~pebbles/ for more information.

The applications to be demonstrated include:

* Personal Universal Controller: The PDA can be used as a remote control for everyday appliances. In our design, the appliance will send a description of its control parameters to the handheld device. The handheld uses this information to automatically create high-quality graphical control panels and a speech user interface. The user can then control the appliance using the handheld or by speaking. We will demonstrate remote-control of video and stereo equipment.

* SlideShow Commander: This allows PDAs to remotely control Microsoft PowerPoint. The presenter can move forward and backwards through the show. The picture and notes of the current slide are displayed on the PDA, or a list of slide titles can be presented. You can scribble on top of the thumbnail picture and the scribbles will appear on the PC screen.

* Remote Commander: This allows one or more PDAs to be used as if they were the PC's cursor and keyboard.

* Shortcutter: Create custom panels to speed up common tasks on the PC.

* Laser Tracking and "Semantic Snarfing". The PC can track the location of a laser pointer, and adjust the cursor or scribble accordingly. The contents around the laser point can be copied ("snarfed") to the handheld for detailed work.

top

Atrium area

A video based interface to textual information for the visually impaired.
Ali Zandifar (University of Maryland) will give a demo on a video-based interface to textual information which reads a flat page and converts the content into speech using TTS(text-to-speech) and off-the-shelf OCR software. The software provides different functionalities such as auto-focus, auto-zoom, image mosaicing to rectify and enhance the quality of a video captured from a flat page before passing to OCR software. The contribution of a demo is to present a real-time integrated system able to read a flat page and convert it to speech.

Fluency:
The Fluency software uses automatic speech recognition and intelligent tutoring techniques to pinpoint errors in a nonnative speaker's pronunciation of English and provide immediate feedback with correction help. The system adapts to the user - her pace, way of learning and native language. Tests have shown that students using the system do as well or better than students in a classroom situation.

iWave: a car gesture interface to control navigation and entertainment:
General Motors approached a team of HCI masters students to design an innovative human-car interface that incorporated low-impedance interaction styles like gestures to support information or entertainment goals without compromising safety.  The team will share lessons learned about designing successful gesture interfaces by showing how the system evolved over three months of extensive usability testing.

Speech Synthesis presented by Alan Black

Ability to Inform Person Identification by Jeff Cohn

top

• Questions?
  Contact Céline