Exportar Publicação

Rustullet, S., Daniela Braga & Dias, J. (2008). Automatic word stress marking and syllabification for Catalan TTS. In Interspeech 2008. (pp. 1889-1892). --: ISCA.

R. S. et al.,  "Automatic word stress marking and syllabification for Catalan TTS", in Interspeech 2008, --, ISCA, 2008, pp. 1889-1892

@inproceedings{s.2008_1732209112053,
	author = "Rustullet, S. and Daniela Braga and Dias, J.",
	title = "Automatic word stress marking and syllabification for Catalan TTS",
	booktitle = "Interspeech 2008",
	year = "2008",
	editor = "",
	volume = "",
	number = "",
	series = "",
	pages = "1889-1892",
	publisher = "ISCA",
	address = "--",
	organization = "",
	url = "https://www.isca-speech.org/archive/interspeech_2008/"
}

TY  - CPAPER
TI  - Automatic word stress marking and syllabification for Catalan TTS
T2  - Interspeech 2008
AU  - Rustullet, S.
AU  - Daniela Braga
AU  - Dias, J.
PY  - 2008
SP  - 1889-1892
CY  - --
UR  - https://www.isca-speech.org/archive/interspeech_2008/
AB  - In this paper, a rule-based automatic syllabifier for Danish is
described using the Maximal Onset Principle. Prior success
rates of rule-based methods applied to Portuguese and Catalan
syllabification modules were on the basis of this work. The
system was implemented and tested using a very small set of
rules. The results gave rise to 96.9% and 98.7% of word
accuracy rate, contrary to our initial expectations, being
Danish a language with a complex syllabic structure and thus
difficult to be rule-driven. Comparison with data-driven
syllabification system using artificial neural networks showed
a higher accuracy rate of the former system.
Index Terms: automatic syllabification, rule-based
techniques, artificial neural networks, text-to-speech.

Index Terms: Catalan text-to-speech, stress, orthographic and phonologic syllabification, prosody 
ER  -