Control of spectral dynamics in concatenative speech synthesis.

Control of spectral dynamics in concatenative speech synthesis.

Current speech synthesis methods based on the concatenation of waveform units can produce highly intelligible speech capturing the identity of a particular speaker. However, the quality of concatenated speech often suffers from discontinuities between the acoustic units, due to contextual difference...

Ausführliche Beschreibung

Bibliographische Detailangaben
Veröffentlicht in:IEEE Transactions on speech and audio processing 9, 1 (2001).
1. Verfasser: Wouters, J.
Format: Artikel
Sprache:English
Schlagworte:
Acoustic transitions.
Acoustic units discontinuities.
Articulation control.
Concatenated speech quality.
Concatenation units.
Concatenative speech synthesis.
Concatenative synthesizer.
Database.
High intelligible speech.
High-quality resynthesis.
Modified spectral shape.
Natural speech.
Signal processing.
Sinusoidal modeling.
Speaking style variations.
Spectral dynamics control.
Spectral mismatch reduction.
Unit fusion.
Unit fusion method.
Waveform units.