A Generative Model of a Pronunciation Lexicon for Hindi
This addresses a domain-specific problem for Hindi voice browser applications, but it is incremental as it applies existing methods to new data.
The paper tackles the need for a pronunciation lexicon in Hindi TTS and ASR systems by developing a generative model that automatically outputs phoneme and prosodic structure levels, including syllable-division and stress placement.
Voice browser applications in Text-to- Speech (TTS) and Automatic Speech Recognition (ASR) systems crucially depend on a pronunciation lexicon. The present paper describes the model of pronunciation lexicon of Hindi developed to automatically generate the output forms of Hindi at two levels, the <phoneme> and the <PS> (PS, in short for Prosodic Structure). The latter level involves both syllable-division and stress placement. The paper describes the tool developed for generating the two-level outputs of lexica in Hindi.