GRAPHEME-TO-PHONE TRANSCRIPTION ALGORITHM FOR TEXT-TO-SPEECH SYSTEMS IN EUROPEAN PORTUGUESE

• Autor(a) principal: Braga, Daniela
• Data de Publicação: 2019
• Tipo de documento: Artigo
• Idioma: eng
• Título da fonte: Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos)
• Texto Completo: https://doi.org/10.34630/polissema.vi6.3320
• topic: Conversão Grafema-fone; Regras Fonológicas; Processamento da Fala; Sistemas de Conversão Texto-fala; Grapheme-to-phone Conversion; Phonological Rules; Speech Processing; Text-to-speech Systems

In this paper, a linguistically rule-based grapheme-to-phone (G2P) transcription algorithm is described for European Portuguese (EP). A G2P, together with the stress determination and the syllable division, is an essential tool in the general architecture of a Text-to-Speech (TTS) system. The G2P is part of the text pre-processing module of the TTS system and its purpose is to convert text into a phonetic transcription that is interpreted by the synthesis engine.A complete set of phonological and phonetic transcription rules regarding the European Portuguese standard variety is presented. This algorithm was implemented under the C++ framework and tested by using online newspaper articles. The obtained experimental results gave rise to 98,80% of accuracy rate. Future developments in order to increase this value are foreseen. Our purpose with this work is to develop a module/tool that can improve synthetic speech naturalness in European Portuguese. Other applications of this system can be expected like language teaching/learning. These results, together with our perspectives of future improvements, have proved the dramatic importance of linguistic knowledge on the development of TTS.The present paper is organized as follows: in section 1, it is made the state-of-the-art on this subject and the justification of our approach; in section 2, the annotation conventions are described, the G2P algorithm is presented and some details on the implementation are shown; in section 3, results are discussed and in section 4 some conclusions and future work are presented.