| Grant number: | 11/01299-4 |
| Support Opportunities: | Scholarships in Brazil - Doctorate |
| Start date: | September 01, 2011 |
| End date: | February 28, 2015 |
| Field of knowledge: | Linguistics, Literature and Arts - Linguistics |
| Principal Investigator: | Claudia Zavaglia |
| Grantee: | Vanessa Marquiafável Serrani |
| Host Institution: | Instituto de Biociências, Letras e Ciências Exatas (IBILCE). Universidade Estadual Paulista (UNESP). Campus de São José do Rio Preto. São José do Rio Preto , SP, Brazil |
| Associated scholarship(s): | 14/00613-5 - Verbs pronunciation system: a proposal for the Brazilian Portuguese, BE.EP.DR |
Abstract This project is dedicated to building a Web environment to support automatic phonetic transcription of entries in Brazilian Portuguese Dictionaries. The motivation for building this environment came from the existing large correspondence between the characters of the spelling alphabet of Brazilian Portuguese and their respective sounds, which we believe will contribute to building a computational tool that makes conversion of orthographic symbols to their sound in a automatically and satisfactorily manner. Thus, the assumption that guides this project is that from a set of computer applications may be possible to convert characters of isolated lexical units (entries) in their corresponding sound units, with the application of a fixed set of objective criteria and annotation, doing so without any type of human intervention. The conversion between orthographic unit (entry input system) and phonetically transcribed lexical unit (system output) will be based on the sources of the standard International Phonetic Alphabet (IPA). Along the types of speech to be transcribed from the entries, this will follow the current trend to reflect a model of speech as universal as possible, general and neutral, without language varieties in current use. Methodologically, the development of the environment involve Corpus Linguistics, Phonetics and Phonology for the construction of a phonetic dictionary of large vocabulary, form which will be extracted phonetic transcriptions for the training of the tool. Its metodology also envolves the use of the working methods of computing to construct the proposed system with instruments of knowledge validation of Statistics (Kappa) to measure the quality of the transcribed corpus. (AU) | |
| News published in Agência FAPESP Newsletter about the scholarship: | |
| More itemsLess items | |
| TITULO | |
| Articles published in other media outlets ( ): | |
| More itemsLess items | |
| VEICULO: TITULO (DATA) | |
| VEICULO: TITULO (DATA) | |