A Finite State and Rule-based Akshara to Prosodeme (A2P) Converter in Hindi
This work addresses the need for accurate prosodic conversion in Hindi, which is incremental as it applies existing finite state and rule-based methods to this specific language task.
The paper tackles the problem of converting Hindi graphemes to prosodemes (phoneme sequences with syllable boundaries and prosodic labels) by developing a finite state and rule-based software module, achieving over 99% accuracy on a lexicon of 28,664 words.
This article describes a software module called Akshara to Prosodeme (A2P) converter in Hindi. It converts an input grapheme into prosedeme (sequence of phonemes with the specification of syllable boundaries and prosodic labels). The software is based on two proposed finite state machines\textemdash one for the syllabification and another for the syllable labeling. In addition to that, it also uses a set of nonlinear phonological rules proposed for foot formation in Hindi, which encompass solutions to schwa-deletion in simple, compound, derived and inflected words. The nonlinear phonological rules are based on metrical phonology with the provision of recursive foot structure. A software module is implemented in Python. The testing of the software for syllabification, syllable labeling, schwa deletion and prosodic labeling yield an accuracy of more than 99% on a lexicon of size 28664 words.