Speech Prosody 2006

Dresden, Germany
May 2-5, 2006

Automatic Construction of a Prosodically Rich Text Corpus for Speech Synthesis Systems

Tanya Lambert

This paper presents a method for an automatic compilation of a phonologically rich text database, which is used in a concatenative text-to-speech (TTS) synthesis system. In this method, linguistic features are predicted from text using Festivalís linguistic engine. A set of phonological units for a specific text is compiled from attribute value lists (AVLs). Phrases/sentences that contain the phonological units that are not included in the database are added to the database. This is an efficient way for generating database prompts with a specific prosodic content; the prompts can then be recorded and converted into voice. The method described here can be used for languages other than English.

Full Paper

Bibliographic reference.  Lambert, Tanya (2006): "Automatic construction of a prosodically rich text corpus for speech synthesis systems", In SP-2006, paper 200.