A Situational Speech Synthesizer for Yoruba: System Design, Phonological Rule Architecture, and Orthographic Extensions for Contour
TTSYoruba is a rule-based speech synthesizer for Yoruba personal names, deployed online for pronunciation guidance. It uses a 651-unit diphone corpus and a four-module pipeline to convert text into audio. The system handles complex tonal rules and nasal disambiguation, including new orthographic extensions for contour tones using caron and circumflex marks.