Advanced Speaker Embedding with Predictive Variance of Gaussian Distribution for Speaker Adaptation in TTS.
Jaeuk LeeJoon-Hyuk ChangPublished in: INTERSPEECH (2022)
Keyphrases
- gaussian distribution
- speaker adaptation
- maximum likelihood
- speech recognition
- speaker dependent
- text to speech
- gaussian mixture model
- expectation maximization
- automatic speech recognition
- speaker identification
- mixture model
- vector space
- em algorithm
- speaker recognition
- prosodic features
- hidden markov models
- pattern recognition
- speech recognizer
- speaker independent
- bayesian networks