A rule-based approach to generating large phonetic databases for Romanian results of the AFLR project

This paper presents a rule-based approach for generating a large phonetic database for Romanian. The knowledge base is developed by means of the GRAALAN (Grammar Abstract Language) system. By inspecting dictionaries and corpora, we generate a phonetic database over 100,000 lemmas. Our database has a high degree of accuracy ensured by our rule-based method applied for generating phonetic transcriptions.