Speech synthesis techniques. A survey

The goal of this paper is to provide a short but a comprehensive overview of Text-To-Speech synthesis by highlighting its digital signal processing component. First two rule-based synthesis techniques (formant synthesis and articulatory synthesis) are explained then the concatenative synthesis is explored. Concatenative synthesis is simpler than rule-based synthesis, since there is no need to determine speech production rules. However, it introduces the challenges of prosodic modification to speech units and resolving discontinuities at unit boundaries. Prosodic modification results in artifacts in the speech that make the speech sound unnatural. Unit selection synthesis, which is a kind of concatenative synthesis, solves this problem by storing numerous instances for each unit with varying prosodies. The unit that best matches the target prosody is selected and concatenated. To resolve mismatches speech synthesis system combines the unit-selection method with Harmonic plus Noise Model (HNM). This model represents speech signal as a sum of a harmonic and noise part. The decomposition of speech signal into these two parts enables more natural sounding modifications of the signal. Finally Hidden Markov model(HMM) synthesis combined with an HNM model is introduced in order to obtain a Text-To-Speech system that requires smaller development time and cost.