PRODUCTION OF LSP PARAMETER SEQUENCES FOR SPEECH SYNTHESIS BASED ON NEURAL-NETWORK APPROACH

This paper presents a generating method of LSP parameter sequences for speech synthesis by rule. In our method, neural networks are schemed to generate LSP parameter sequences of Vowel-Consonant-Vowel(VCV) unit s. The quality of synthesized speech by concatenation way of VCV units through table-look-up technique can not be improved so much owing to the distortion appearing on VCV units junction. In our method, the neu ral networks concatenate VCV units step by step with less distortion o n VCV units junction, which synthesizes good quality speech.