Reading Numbers Algorithm for Portuguese

Abstract The paper presents an algorithm for read common numbers until one million in Portuguese language. The record and cutting process of the numbers speech sounds deserved a special attention to improve the speech sound output. A special attention is required for the correct inclusion of particles to provide better naturalness of the read numbers. The system has the ability of simulate the human biologic speech sound production in the task of reading numbers. The system is based on biologic speech. The naturalness of the system can be improved using speech files of read numbers in different position (beginning, middle and end) and using numbers concatenated with the particle ‘e’. A final F0 modification can improve the final speech quality of the system.