This paper presents an approach to letter-to-sound translation for the Polish language that is a part of a speech recognition system. It describes the process of automatic generation of Polish letter-to-sound (LTS) rules. The LTS rules were trained with a Polish phonetic lexicon, that was extracted from the “wictionary” - a Polish on-line dictionary. This lexicon contains 35.826 entries. We examined a novel method for creating the letter-to-phone allowable pairing, that applies the “IBM Model 1 algorithm. Such automatically generated allowed letter-to-sound pairs were compared with a second pairing map, created by an expert. Both allowable pairing maps were used separately to train the Polish LTS rules. The test results verify that our generated pairing map leads to a more compact LTS model than the expert-made one.
[1]
Paul Lamere,et al.
Sphinx-4: a flexible open source framework for speech recognition
,
2004
.
[2]
Alan W Black,et al.
Festvox : Tools for Creation and Analyses of Large Speech Corpora
,
2010
.
[3]
Wlodzimierz Kasprzak,et al.
Stochastic Modelling of Sentence Semantics in Speech Recognition
,
2011,
Computer Recognition Systems 4.
[4]
Stefan Grocholewski,et al.
Statystyczne podstawy systemu ARM dla języka polskiego
,
2001
.
[5]
Paul Taylor,et al.
The architecture of the Festival speech synthesis system
,
1998,
SSW.
[6]
Philip Koehn,et al.
Statistical Machine Translation
,
2010,
EAMT.