Back to search

National and Kapodistrian University of Athens

Μοντελοποίηση της ακουστικής αναπαράστασης της τυπογραφίας εγγράφων μέσω εκφραστικής συνθετικής ομιλίας για τυφλούς και βλέποντες

Abstract

dc:description

The accessibility to printed and electronic documents (books, newspapers, journals, letters, web content) by the print disabled, as well as the moving users and the elderly, is based on the possibility to convert them (in real time) into, primary, acoustic and or haptic modality. Besides its content, a printed or electronic text document contains a number of presentation visual elements that apply design glyphs or typographic elements, such as font (type, size and color) and font style (bold, italics and underline). Regardless the important progress achieved in Text-to-Speech systems, to date they do not support the efficient sonification of the semantics and cognitive aspects of the Visual Presentation Elements in Documents (VPED). Essentially all this additional metadata vanishes during the document processing towards its acoustic or haptic (in Braille) rendition.This dissertation deals with the sonification of the VPED metadata during their transformation to speech. The approach to this problem includes two phases: a) the automatic extraction of the VPED induced emotional states to the reader and b) their acoustic rendition using expressive emotional synthetic speech. Focusing on the develop a system for the automatic extraction of the VPED induced emotional states and the appropriate tagging of the documents with this information, a novel architecture is proposed for the multimodal universal accessibility of documents, regardless of their natural language, content and culture. The realization of the corresponding system is based on the XML technology. Moreover, a quantitative model is developed for the sonification of the VPED typographic alternations by: i) the mathematical formulation of the induced reader’s emotional state, based on the dimensional nature of the emotions in the space “Pleasure”, “Arousal” and “Dominance”, and ii) their mapping into prosodic alternation of the expressive synthetic speech. For the evaluation of the prosodic model we have explored, using psychoacoustic experiments, whether the listeners can acoustically recognize the VPED typographic alternations. The results were positive even in the case of listeners without any previous training. Furthermore, the evaluation of the developed model by sighted and blind students of primary education shows enhancement of their performance during the didactic process.

Degree

thesis:*
Grantor dc:publisher
National and Kapodistrian University of Athens
Year dc:date
2012

Author and committee

dc:creator, dc:contributor.*
Authors dc:creator
  • Tsonos, Dimitrios
  • Τσώνος, Δημήτριος

Subjects

dc:subject × 14

Rights

Language dc:language
gre

Identifiers

dc:identifier.*
Identifier
10.12681/eadd/33257

Chain of custody

source
Harvested from
Greek National Archive of PhD Theses
Base URL
phdtheses.ekt.gr/eadd_oai/request
Last updated
2026-11-18
Source record
OAI-PMH GetRecord
citation

Tsonos, Dimitrios; Τσώνος, Δημήτριος. Μοντελοποίηση της ακουστικής αναπαράστασης της τυπογραφίας εγγράφων μέσω εκφραστικής συνθετικής ομιλίας για τυφλούς και βλέποντες. National and Kapodistrian University of Athens, 2012. http://hdl.handle.net/10442/hedi/33257