Unsupervised Learning of a Disentangled Speech Representation for Voice Conversion.
Tobias GburrekThomas GlarnerJanek EbbersReinhold Haeb-UmbachPetra WagnerPublished in: SSW (2019)
Keyphrases
- unsupervised learning
- speech recognition
- neural network
- text to speech
- dimensionality reduction
- image representation
- speech recognition errors
- computer vision
- image processing
- hidden markov models
- human computer interaction
- speech signal
- automatic speech recognition
- deep learning
- speech synthesis
- text to speech synthesis