Joint prosody prediction and unit selection for concatenative speech synthesis
2002Vol. 2, pp. 781–784
Citations Over TimeTop 10% of 2002 papers
Abstract
We describe how prosody prediction can be efficiently integrated with the unit selection process in a concatenative speech synthesizer under a weighted finite-state transducer (WFST) architecture. WFSTs representing prosody prediction and unit selection can be composed during synthesis, thus effectively expanding the space of possible prosodic targets. We implemented a symbolic prosody prediction module and a unit selection database as the synthesis components of a travel planning system. Results of perceptual experiments show that by combining the steps of prosody prediction and unit selection we are able to achieve improved naturalness of synthetic speech compared to the sequential implementation.
Related Papers
- → PAVITS: Exploring Prosody-Aware VITS for End-to-End Emotional Voice Conversion(2024)9 cited
- → A new Chinese text-to-speech system with high naturalness(2002)15 cited
- → Automatic Prosody Generation(1997)1 cited
- → Text to speech synthesis(2024)1 cited
- → Prosody Correction Preserving Speaker Individuality for Chinese-Accented Japanese HMM-Based Text-to-Speech Synthesis(2019)