Letter-To-Sound Conversion For Urdu Text-To-Speech System

Phonological Processing for Urdu Text to Speech System

Determining and modeling phonological phenomena is necessary to generate speech from textual input. These phenomena include letter to sound conversion, syllabification, sound change, stress assignment and intonation assignment. This paper presents work on Urdu phonological processes and provides algorithms to convert textual input into phonologically annotated output, required for Urdu text-to-...

Automatic Diacritization for Urdu

Urdu language is written in Arabic script. In this script, the consonantal context is clearly represented, but the vocalic sounds are represented (mostly) by marks or diacritics, which are optional and normally not written. Readers can guess the diacritics and thus can pronounce words correctly, based on their knowledge of the language. But un-diacritized Urdu text creates ambiguity for novice ...

Dialect variation in Boro Language and Grapheme-to-Phoneme conversion rules to handle lexical lookup fails in Boro TTS System

It is not possible to include all the words in a natural language for general text-to-speech system. Grapheme-tophoneme conversion system is essential to pronounce a word which is out of vocabulary. Grapheme-to-phoneme rules play a vital role where lexical lookup fails. Though basic Grapheme-tophoneme rules system is very simple yet it is very powerful for naturalness of a TTS system. Letter-to...

A Comparison of Letter-to-sound Conversion Techniques for English Text-to- Speech Synthesis

Subjective Testing of Urdu Text-to-Speech (TTS) System

Text-to-speech (TTS) systems for many widely spoken languages have been developed and evolved over the last few decades. Such systems are being used in many different fields. Since these TTS systems have differences in the perceived sound quality, many speech quality test methods have been proposed to compare and evaluate their performance. Test materials for these tests, however, are language ...