Applying the harmonic plus noise model in concatenative speech synthesis.

This paper describes the application of the harmonic plus noise model (HNM) for concatenative text-to-speech (TTS) synthesis. In the context of HNM, speech signals are represented as a time-varying harmonic component plus a modulated noise component. The decomposition of a speech signal into these t...

Descrición completa

Detalles Bibliográficos
Publicado en:	IEEE Transactions on speech and audio processing 9, 1 (2001).
Autor Principal:	Stylianou, Y.
Formato:	Artigo
Idioma:	inglés
Subjects:	Acoustic units. Adapted schemes. Concatenative text-to-speech synthesis. Discontinuities smoothing. Formal listening tests. Harmonic plus noise model. High-quality speech synthesis. Modulated noise component. Natural-sounding signal modifications. Parametric speech representation. Speech intelligibility. Speech naturalness. Speech pleasantness. Speech signal decomposition. Speech signals representation. Time-varying harmonic component.