Multi-stage attention for fine-grained expressivity transfer in multispeaker text-to-speech system.
Ajinkya KulkarniVincent ColotteDenis JouvetPublished in: EUSIPCO (2022)
Keyphrases
- fine grained
- multistage
- text to speech
- coarse grained
- speech synthesis
- single stage
- stochastic programming
- production system
- dynamic programming
- stochastic optimization
- prosodic features
- access control
- programming tool
- tightly coupled
- lot sizing
- massively parallel
- transfer learning
- lot streaming
- word processing
- attack detection
- writing skills
- data lineage
- text to speech synthesis
- relational databases