This paper is about constructing sharable linguistic information to be used across languages for a Text-to-Speech (TTS) system. The data is obtained from existing resources. The focus of the paper is the phonetic and linguistic aspects. A monolingual TTS architecture is introduced with descriptions on each stage of processing. A multilingual TTS architecture is also introduced. Language dependent and language independent information required in the general TTS engine is described. Finally we will propose layer of communication between the pooled language information and a TTS engine in order to make it available for information reuse where possible for different languages.
|Title of host publication||AISB 2011: Learning Language Models from Multilingual Corpora|
|Number of pages||5|
|Publication status||Published - 1 Jan 2011|