This paper describes ongoing work which aims to produce a methodology for automatically deriving several prosody models, each suited for text-to-speech synthesis of a specific text type. As part of this work an experiment is described in which human readings of documents covering 10 common text types (news, weather forecasts, etc) were analysed for their acoustic/prosodic properties. This was c...

Do structural patterns tell us something about the text content? In order to give a preliminary answer to this question, an experiment in automatic text classification is performed using only surface-structural features. The features extracted – as, e.g., the complexity, length or depth of text constituents (Köhler, 1999), – produced surprisingly good classification results. This finding argues...

This is a normal text in 10 pt type size and 12 pt line spacing. This is a normal text in 10 pt type size and 12 pt line spacing. This is a normal text in 10 pt type size and 12 pt line spacing. This is a normal text in 10 pt type size and 12 pt line spacing. This is a normal text in 10 pt type size and 12 pt line spacing. This is a normal text in 10 pt type size and 12 pt line spacing. This is...