Improving Unsupervised Style Transfer in end-to-end Speech Synthesis with end-to-end Speech Recognition.
Da-Rong LiuChi-Yu YangSzu-Lin WuHung-yi LeePublished in: SLT (2018)
Keyphrases
- end to end
- speech synthesis
- speech recognition
- hidden markov models
- vocal tract
- speech processing
- language model
- text to speech
- congestion control
- pattern recognition
- speech signal
- noisy environments
- speech recognition technology
- automatic speech recognition
- speech recognizer
- speaker identification
- image processing
- machine learning
- noise reduction
- image quality
- motion estimation
- bayesian networks
- speaker independent
- isolated word