|
Veranstalter
|
|
Carola Eschenbach,
Christopher Habel,
Wolfgang Menzel,
Felix Lindner,
Matthias Kerzel,
Timo Baumann
|
|
Zeit/Ort
|
|
Di 16-18 F-534, Beginn: |
|
Inhalt
|
|
Vorträge über Vorhaben und Ergebnisse von Bachelor-, Master- und Diplomarbeiten,
laufenden Dissertationen und Drittmittelprojekten sowie von anderen Forschungsarbeiten aus
dem Bereich der Wissens- und Sprachverarbeitung. Insbesondere wird der interdisziplinäre
Charakter des Forschungsschwerpunktes berücksichtigt, d.h. die Integration von Ansätzen der
Informatik, Linguistik, Logik und Psychologie steht im Vordergrund der Arbeiten. |
|
Termine
|
|
| 17.04.2012 |
Dies Academicus (kein Vortrag)
|
|
|
| 24.04.2012 |
Timo Baumann
Incremental Speech Synthesis
Incremental speech synthesis (iSS) accepts input and produces output in
consecutive chunks that only together result in a full utterance. iSS is useful
to minimize system onset time, to allow for timely integration of user feedback,
or other events. I will present recent and ongoing work on incrementalizing
speech synthesis, results that show that using iSS can be highly profitable in
quickly adapting to changes, allows for more prompt reaction and leads to only
marginally declined performance compared to non-incremental
synthesis.
|
|
|
| 01.05.2012 |
Tag der Arbeit (kein Vortrag)
|
|
|
| 08.05.2012 |
CINACS-Kolloquium: Beginn 17:15 Uhr
Christoph Schlieder
Image-based Place Models for Geographic Recommendations
Classical recommender systems solve an information filtering task. They
suggest a data object, typically a text document describing some product or
service, that is likely to be relevant to the user based upon her or his
previous choices. A geographic recommender system recommends items from a
library of geo-referenced objects. In multi-object recommendation, collections
of items are suggested which should consist of somehow similar exemplars but, at
the same time, must show variability. A geographic multi-object recommender
suggests, for instance, a list of cities to visit or a slide show of images
illustrating a certain place.
The talk gives an introduction into the
research field and presents the approach taken by our Tripost multi-object
recommender for selecting a small set of geo-referenced images of a touristic
location. Motivated by this research, we ask how different conceptualizations of
a city can be identified in web-based image collections. The method is
illustrated by analyzing image data set from the cities of Amsterdam, Bamberg,
Cardiff, and Dublin. In addition, the talk presents a recently collected data
set of GPS tracks and geo-referenced photographs taken from visitors of the Old
Town of Bamberg. Our data suggests that differences in the frequency of spatial
choices need to be taken into account when building place models for recommender
systems.
|
|
|
| 15.05.2012 |
Ole Eichhorn
Generating Situated Assisting Utterances to Facilitate Tactile-Map Understanding: A Prototype System
Tactile maps are important substitutes for visual maps for blind and
visually impaired people and the efficiency of tactile-map reading can be
improved by giving assisting utterances that make use of spatial language. In
this talk, earlier ideas for a system that generates such utterances are
elaborated. A prototype implementation based on a semantic conceptualization of
the movements that the map user performs is presented. An example shows the
plausibility of the solution and the output that the prototype generates.
|
|
|
| 22.05.2012 |
Junlei Yu
A Haptic-Audio Interface for Acquiring Spatial Knowledge about Apartments
In selecting an apartment for residence, floor plans are a common source
of relevant information. For visually impaired people, adequate floor plans are
widely missing. This paper introduces a haptic-audio assistance sys- tem, which
is designed and implemented to help visually impaired people to acquire the
layout of novel small-scale apartments. Virtual 2.5-D floor plan models are made
according to realistic?traditional visual?floor plans. Haptic force feedback
will be rendered when users explore the virtual model by a PHANToM Omni device.
During the exploration, auditory assistance informa- tion, in the form of either
speech or sonification, is invoked by entering into prescribed areas, which are
placed on the inner contour of every area. Two user studies are presented which
demonstrate the usability of the haptic-audio inter- face. In particular,
reinforcement and extra positive influence brought by the employment of multiple
modes in audio perception channel is confirmed.
|
|
|
| 19.06.2012 |
Felix Lindner
Affordances and Affordance Spaces from the Perspective of a Social Robot
Social robots have to coordinate their actions considering the spatial
requirements of the humans with whom they interact. The talk introduces a
general framework based on the notion of affordances that generalizes
geometrical accounts to the problem of human-aware robot placement. The
framework provides a conceptual instrument to take into account the
heterogeneous abilities and dipositions of humans, robots, and environmental
entities. It is discussed how affordance knowledge enables perspective taking
and how it can be used in various reasoning tasks relevant to human-robot
interaction.
|
|
|
| 10.07.2012 |
CINACS-Kolloquium: Beginn 17:15 Uhr
Cengiz Acartürk
Communication through line graphs: Graphical cues, gestures and haptic line graphs
Statistical line graphs are widely used in daily-life communication
settings, including newspapers, research reports and scientific articles. Human
communication through line graphs involves the contribution of multiple sensory
modalities, such as vision, audio, gesture and haptics, as well as multiple
representations in the same sensory modality, such as graphical entities and
language in written form, both are in visual modality. In the first part of the
talk, I will present a set of experimental investigations, in which human
participants were asked to sketch graphical cues on time-domain line graphs, to
verbally describe graphically-cued sketches and to predict verbalized graphs
among alternative representations. In the second part of the talk, the plan for
future research on haptic line graphs will be presented.
|
|
