Gerasimos Xydas

Learn More
Text documents usually embody visually oriented meta-information in the form of complex visual structures, such as tables. The semantics involved in such objects result in poor and ambiguous text-to-speech synthesis. Although most speech synthesis frameworks allow the consistent control of an abundance of parameters, such as prosodic cues, through(More)
The prosodic specification of an utterance to be spoken by a Text-to-Speech synthesis system can be devised in break indices, pitch accents and boundary tones. In particular, the identification of break indices formulates the intonational phrase breaks that affect all the forthcoming prosody-related procedures. In the present paper we use tree-structured(More)
Electronic texts carry important meta-information (such as tags in HTML) that most of the current Text-to-Speech (TtS) systems ignore during the production of the speech. We propose an approach to exploit this meta-information in order to achieve a detailed auditory representation of an e-text. The e-Text to Speech and Audio (e-TSA) Composer has been(More)
Emerging electronic text formats include hierarchical structure and visualization related information that current Text-to-Speech (TtS) systems ignore. In this paper we present a novel approach for composing detailed auditory representation of e-texts using speech and audio. Furthermore, we provide a scripting language (CAD scripts) for defining specific(More)
Transferring a structure from the visual modality to the aural one presents a difficult challenge. In this work we are experimenting with prosody modeling for the synthesized speech representation of tabulated structures. This is achieved by analyzing naturally spoken descriptions of data tables and a following feedback by blind and sighted users. The(More)
A significant challenge in Text-to-Speech (TtS) synthesis is the formulation of the prosodic structures (phrase breaks, pitch accents, phrase accents and boundary tones) of utterances. The prediction of these elements robustly relies on the accuracy and the quality of error-prone linguistic procedures, such as the identification of the part-of-speech and(More)
SUMMARY Synthetic speech usually suffers from bad F0 contour surface. The prediction of the underlying pitch targets robustly relies on the quality of the predicted prosodic structures, i.e. the corresponding sequences of tones and breaks. In the present work, we have utilized a linguistically enriched annotated corpus to build data-driven models for(More)
This paper presents a methodology for the real-time extraction of readers' emotional state from documents as well as the representation of emotionally annotated documents into acoustic modality. Using the Self Assessment Manikin Test we performed preliminary experiments on the extraction of Pleasure – Arousal – Dominance (P.A.D.) annotation rules that the(More)
There are two issues that are challenging in the life-cycle of Digital Talking Books (DTB): the automatic labeling of text formatting meta-data in documents and the multimodal representation of the text formatting semantics. We propose an augmented design-for-all approach for both the production and the reading processes of DAISY compliant DTBs. This(More)