Empirical Study of Speech Synthesis Markup Language and Its Implementation for Punjabi Language

This paper builds a prioritized list of requirements for speech synthesis markup which any proposed markup language should address. This study presents requirements and essential tags for specification development of Punjabi Language. A speech synthesizer works like written text into correct sounds to be spoken. To do this it uses an SSML document and one or more lexicons and dictionaries. We have presented how the different type of modules in TTS System helps to convert a text input of SSML document to spoken form in Punjabi Language. Since, Punjabi is the morphological rich Language, it is written in "Gurumukhi" Script and this is the official Language of Govt. of India. So, hence accordingly in this language Homograph problem will not occur. Tones in Punjabi pose big problems. The words written in similar ways, have different tones and there by changes their meanings for which the tags have been designed separately. In Punjabi orthographically the written symbols exactly corresponds to the specific words. Therefore in Punjabi, we do not any word which may be called Homograph.