Ontology for a voice transcription of OpenStreetMap data: the case of space apprehension by visually impaired persons

Abstract

In this paper, we present a vocal ontology of
OpenStreetMap data for the apprehension of space by visually
impaired people. Indeed, the platform based on produsage gives a
freedom to data producers to choose the descriptors of geocoded
locations. Unfortunately, this freedom, called also folksonomy leads
to complicate subsequent searches of data. We try to solve this issue
in a simple but usable method to extract data from OSM databases in
order to send them to visually impaired people using Text To Speech
technology. We focus on how to help people suffering from visual
disability to plan their itinerary, to comprehend a map by querying
computer and getting information about surrounding environment in
a mono-modal human-computer dialogue.

Document type: Conference object

Full document

Original document

The different versions of the original document can be found in:

• https://hal.archives-ouvertes.fr/hal-01674549 under the license http://hal.archives-ouvertes.fr/licences/publicDomain/

• https://zenodo.org/record/1130559

• https://hal.archives-ouvertes.fr/hal-01533064,

https://hal.archives-ouvertes.fr/hal-01533064/document,

https://hal.archives-ouvertes.fr/hal-01533064/file/waset_Londres.pdf under the license http://creativecommons.org/licenses/by/4.0/legalcode

• https://zenodo.org/record/1130559,

http://dx.doi.org/10.5281/zenodo.1130558 under the license http://hal.archives-ouvertes.fr/licences/publicDomain/

• https://zenodo.org/record/1130559,

http://dx.doi.org/10.5281/zenodo.1130559 under the license https://creativecommons.org/licenses/by/4.0

under the license https://creativecommons.org/licenses/by/4.0

DOIS: 10.5281/zenodo.1130558 10.5281/zenodo.1130559