Title :
Automated grapheme-to-phoneme conversion system for Romanian
Author :
József, Domokos ; Ovidiu, Buza ; Gavril, Toderean
Author_Institution :
Commun. Dept., Tech. Univ. of Cluj-Napoca, Cluj-Napoca, Romania
Abstract :
The scope of this paper is to present a novel automated grapheme-to-phoneme conversion system for the Romanian language, based on artificial neural networks together with some transcription results based on a 1.004 words hand built pronunciations dictionary. Using this letter-to-sound transcription system we have also built a large pronunciation dictionary for Romanian language by transcribing the near 140.000 base form entries from the DEXOnline dictionary.
Keywords :
dictionaries; linguistics; neural nets; speech recognition; DEXOnline dictionary; Romanian language; artificial neural network; automated grapheme to phoneme conversion system; letter to sound transcription system; Artificial neural networks; Databases; Dictionaries; Feature extraction; Neurons; Testing; Training; artificial neural network; grapheme-to-phoneme conversion; letter-to-sound transcription; phonetic transcription; pronunciation dictionary;
Conference_Titel :
Speech Technology and Human-Computer Dialogue (SpeD), 2011 6th Conference on
Conference_Location :
Brasov
Print_ISBN :
978-1-4577-0440-6
DOI :
10.1109/SPED.2011.5940736
