Synth2Aug: Cross-domain speaker recognition with TTS synthesized speech.
Yiling HuangYutian ChenJason PelecanosQuan WangPublished in: CoRR (2020)
Keyphrases
- speaker recognition
- cross domain
- synthesized speech
- gaussian mixture model
- vector quantization
- speaker verification
- knowledge transfer
- text categorization
- speaker identification
- transfer learning
- probabilistic neural network
- feature vectors
- e government
- speech recognition
- neural network
- machine learning algorithms
- speech signal
- mixture model
- facial expressions
- probabilistic model
- machine learning
- data mining