Basis Identification for Automatic Creation of Pronunciation Lexicon for Proper Names
This addresses the manual effort in pronunciation lexicon creation for proper names, which is incremental as it builds on existing G2P methods but focuses on a specific bottleneck.
The paper tackles the problem of manually creating pronunciation lexicons for proper names by proposing an optimization approach to automatically construct a small orthogonal basis set of words that spans a database of names, enabling transcription through manual transcription of only this basis. Experiments on a large proper name database show that transcription can be achieved with a small number of basis words, with performance better when names share the same origin.
Development of a proper names pronunciation lexicon is usually a manual effort which can not be avoided. Grapheme to phoneme (G2P) conversion modules, in literature, are usually rule based and work best for non-proper names in a particular language. Proper names are foreign to a G2P module. We follow an optimization approach to enable automatic construction of proper names pronunciation lexicon. The idea is to construct a small orthogonal set of words (basis) which can span the set of names in a given database. We propose two algorithms for the construction of this basis. The transcription lexicon of all the proper names in a database can be produced by the manual transcription of only the small set of basis words. We first construct a cost function and show that the minimization of the cost function results in a basis. We derive conditions for convergence of this cost function and validate them experimentally on a very large proper name database. Experiments show the transcription can be achieved by transcribing a set of small number of basis words. The algorithms proposed are generic and independent of language; however performance is better if the proper names have same origin, namely, same language or geographical region.