An Open Source HMM-based Text-to-Speech System for Brazilian Portuguese

Text-to-speech (TTS) is currently a mature technology that is used in many applications. Some modules of a TTS depend on the language and, while there are many public resources for English, the resources for some underrepresented languages are still limited. This work describes the development of a complete TTS system for Brazilian Portuguese which expands the already available resources. The system uses the MARY framework and is based on the hidden Markov model (HMM) speech synthesis approach. Some of the contributions of this work consist in implementing syllabification, determination of stressed syllable and grapheme-tophoneme (G2P) conversion. This work also describes the steps for organizing the developed resources and implementing a Brazilian Portuguese voice within the MARY. These resources are made available and facilitate the research in text analysis and HMM-based synthesis for Brazilian Portuguese.