sOc-EUSAI'2005 conference

Regular session - New interaction devices
O1-1 Implementing TouchMe Paradigm with a Mobile Phone
Pohjanheimo, Lauri - Keranen, Heikki - Ailisto, Heikki
As formated for the printed proceedings - 9.ps - 9.pdf - pages 87-92
As delivered by the authors - 9_pdf_file.pdf
Abstract :
In earlier papers, the concept of Physical Browsing has been suggested as a natural way to improve the usability of mobile devices and to enable interaction with digital services associated with real world objects in the environment. Since mobile phones are very widely used, it offers a good platform for pervasive applications. In this paper, we realize the Physical Browsing concept using an RFID-reader. With the reader attached to the mobile phone, we invoke digital services embedded in the environment. The implementation of the software needed for ubiquitous use of physical browsing is presented and the feasibility is demonstrated with four concrete examples.


O1-2 A tissue-conductive acoustic sensor applied in speech recognition for privacy
Heracleous, Panikos - Nakajima, Yoshitaka - Saruwatari, Hiroshi - Shikano, Kiyohiro
As formated for the printed proceedings - 33.ps - 33.pdf - pages 93-98
As delivered by the authors - 33_pdf_file.pdf
Abstract :
In this paper, we present the Non-Audible Murmur (NAM) microphones focusing on their applications in automatic speech recognition. A NAM microphone is a special acoustic sensor attached behind the talker's ear and able to capture very quietly uttered speech (non-audible murmur) through body tissue. Previously, we reported experimental results for non-audible murmur recognition using a Stethoscope microphone in a clean environment. In this paper, we also present a more advanced NAM microphone, the so-called Silicon NAM microphone. Using a small amount of training data and adaptation approaches, we achieved a 93.9% word accuracy for a 20k vocabulary dictation task. Therefore, in situations when privacy in humanmachine communication is preferable, NAM microphone can be very effectively applied for automatic recognition of speech inaudible to other listeners near the talker. Because of the nature of non-audible murmur (e.g., privacy) investigation of the behavior of NAM microphones in noisy environments is of high importance. To do this, we also conducted experiments in real and simulated noisy environments. Although, using simulated noisy data the NAM microphones show high robustness against noise, in real environments the recognition performance decreases markedly due to the effect of the Lombard reflex. In this paper, we also report experimental results showing the negative impact effect of the Lombard reflex on non-audible murmur recognition. In addition to a dictation task, we also report a keyword-spotting system based on non-audible murmur with very promising results.


O1-3 Gesture Spotting Using Wrist Worn Microphone and 3-Axis Accelerometer
Ward, Jamie A. - Lukowicz, Paul - Troster, Gerhard
As formated for the printed proceedings - 63.ps - 63.pdf - pages 99-104
As delivered by the authors - 63_pdf_file.pdf
Abstract :
We perform continuous activity recognition using only two wrist-worn sensors - a 3-axis accelerometer and a microphone. We build on the intuitive notion that two very different sensors are unlikely to agree in classification of a false activity. By comparing imperfect, jumping window classifications from each of these sensors, we are able discern activities of interest from null or uninteresting activities. Where one sensor alone is unable to perform such partitioning, using comparison we are able to report good overall system performance of up to 70% accuracy. In presenting these results, we attempt to give a more-in depth visualization of the errors than can be gathered from confusion matrices alone.


O1-4 Facilitating Interaction with Large Displays in Smart Spaces
Bi, Xiaojun - Shi, Yuanchun - Chen, Xiaojie - Xiang, Peifeng
As formated for the printed proceedings - 67.ps - 67.pdf - pages 105-110
As delivered by the authors - 67_pdf_file.pdf
Abstract :
Large displays are widely equipped in Smart Spaces these days. However, traditional interaction devices which are designed to suit desktop screen, such as mice, keyboards, have various limitations in such environments. In this paper, we present a novel human-computer interaction system, known as the CollabPointer, for facilitating interaction with large displays in Smart Spaces. A laser pointer integrated with three additional buttons and wireless communication modules is induced as input device in our system and three features distinguish the CollabPointer from other interaction technologies.
First, the coordinates of the red laser point on the screen emitted by the laser pointer are interpreted as the cursor’s position and the additional buttons on it wirelessly emulate a mouse’s buttons through radio frequency. It enables remote interaction at any distance.
Second, when multiple users are interacting, with two-steps associating methods described in this paper, our system can identify different laser pointers and support multi-user collaboration.
Last but not least, the laser pointer emits its identity through radio frequency during interaction. The system receives it and treats different users separately.
In the end, the CollabPointer has been implemented in the Smart Classroom - a prototype of Smart Space, and the results of user studies show the benefit of it.