DGC-Vector: A New Speaker Embedding for Zero-Shot Voice Conversion.
Ruitong XiaoHaitong ZhangYue LinPublished in: ICASSP (2022)
Keyphrases
- vector space
- synthesized speech
- text to speech
- prosodic features
- speaker recognition
- feature vectors
- similarity search
- speech recognition
- vector data
- speaker verification
- mel frequency cepstral coefficients
- audio visual
- computer vision
- emotion recognition
- automatic speech recognition
- sparse matrix
- speech synthesis
- data hiding
- data conversion
- speech sounds
- pattern recognition