Schwa-Deletion in Hindi Text-to-Speech Synthesis

Abstract

We describe the phenomenon of schwa-deletion in Hindi and how it is handled in the pronunciation component of a multilingual concatenative text-to-speech system. Each of the consonants in written Hindi is associated with an "inherent" schwa vowel which is not represented in the orthography. For instance, the Hindi word pronounced as [namak] ('salt') is represented in the orthography using the consonantal characters for [n], [m], and [k]. Two main factors complicate the issue of schwa pronunciation in Hindi. First, not every schwa following a consonant is pronounced within the word. Second, in multimorphemic words, the presence of a morpheme boundary can block schwa deletion where it might otherwise occur. We propose a model for schwa-deletion which combines a general purpose schwa-deletion rule proposed in the linguistics literature (Ohala, 1983), with additional morphological analysis necessitated by the high frequency of compounds in our database. The system is implemented in the framework of finite-state transducer technology.

Efficient Model for Numerical Text-To-Speech Synthesis System in Marathi, Hindi and English Languages

“…Bhuvana Narasimhan et al [5] have proposed the Hindi TTS-model for schwa-deletion using concatenative technique. There were different issues of schwa pronunciation in Hindi: every schwa following the consonant is not produced within the word; the schwa deletion can be blocked for the presence of a morpheme boundary in multimorphemic words.…”

“…The natural and non-natural language must be expanded into full words. The non-natural language text is to convert into the words [5]. This process is often called verbalization.…”

“…985.92 should be translated into a stream of phones using a graphemeto-phoneme as ‗nine hundred eighty-five and ninety-two coins' in English, ‗ ' in Marathi, ‗ ' in Hindi. The numerical parts of speech can be recognized but it needs speech library [3][4][5][6][15][16][17][18][19]. The next section can be seen how to prepare speech library.…”

“…The human voice range for intensity is from 30 dB to 120 dB. The speech library of Indian numbers with the visual figure in Marathi, Hindi and English is used [5]. Those speech samples are acquired through standard PRAAT tool.…”

“…The emergent technique is worked on the superasegmental which is one type of the prosody. The content of the prosody can be divided into three parts: length, pitch detection and intensity of the speech signals [4,5]. The prosodic features are to apply on the numeric style.…”