SNAC: Speaker-Normalized Affine Coupling Layer in Flow-Based Architecture for Zero-Shot Multi-Speaker Text-to-Speech.
Byoung Jin ChoiMyeonghun JeongJoun Yeop LeeNam Soo KimPublished in: IEEE Signal Process. Lett. (2022)
Keyphrases
- prosodic features
- text to speech
- speaker verification
- speech synthesis
- speech recognition
- speaker recognition
- real time
- multi layer
- automatic speech recognition
- speaker diarization
- speaker identification
- text to speech synthesis
- audio visual
- software architecture
- spontaneous speech
- programming tool
- middle layer
- affine invariant
- online learning
- word processing
- image registration
- pattern recognition
- image sequences
- hierarchical architecture
- high level
- neural network