Phonological analysis is one approach to finding the correct pronunciation of a given text.
It is sometimes called letter-to-sound or grapheme-to-phoneme (G2P) conversion.
Mapping between letters and sounds in Thai is nota straight-forward process.
Table 4 illustrates several problems involved in Thai G2P (Aroonmanakun, 2005;
Tarsaku et al., 2001).
Using only a mapping table or a pronunciation dictionary does not provide sufficient information
for solving the problems presented.
A more complicated phonological analyzer is needed.
The early methods proposed by Meknavin and Kijsirikul (1997b) and Narupiyakul
(1999) were based on complex rules coded by linguists.
To resolve ambiguous cases, statistical models such as an n-gram model
(Chotimongkol and Black, 2000)
and a probabilistic generalized LR parser (PGLR) (Tarsakuet al., 2001) have recently been used