DGC-vector: A new speaker embedding for zero-shot voice conversion.
Ruitong XiaoHaitong ZhangYue LinPublished in: CoRR (2022)
Keyphrases
- vector space
- synthesized speech
- prosodic features
- speaker verification
- feature vectors
- data hiding
- information hiding
- nonlinear dimensionality reduction
- mel frequency cepstral coefficients
- text to speech
- robust image watermarking
- feature selection
- speech synthesis
- speaker identification
- visual features
- image features
- high dimensional