One-Shot Voice Conversion Based on Speaker Aware Module.
Ying ZhangHao CheJie LiChenxing LiXiaorui WangZhongyuan WangPublished in: ICASSP (2021)
Keyphrases
- prosodic features
- synthesized speech
- audio visual
- speaker verification
- emotion recognition
- text to speech
- speech recognition
- automatic speech recognition
- speech sounds
- speech synthesis
- speaker identification
- social networks
- search engine
- speech signal
- artificial neural networks
- pattern recognition
- multiscale
- image sequences
- mel frequency cepstral coefficients
- information systems
- speech quality
- computer vision