Speech synthesis using the CELP algorithm

The paper presents a phoneme/diphone based speech synthesis system for the (Brazilian) Portuguese language. The basic idea of this system is the construction of a library of phonetic units, and processing of those basic units to build an utterance. The system is complemented by a text to phoneme translator described previously. The phonate´s representation in the library is based on a linear prediction model; the filter which models the vocal tract is represented by line spectrum pairs, and the excitation by code excited linear prediction (CELP) parameters. The paper is organized as follows. After a brief introduction, CELP coding is briefly presented and the relevant points to be applied in speech synthesis are presented. The main contribution of the paper is detailing the process of building the phoneme library and the interpolation techniques used