Whispered-to-voiced Alaryngeal Speech Conversion with Generative Adversarial Networks.
Santiago PascualAntonio BonafonteJoan SerràJosé Andrés González LópezPublished in: IberSPEECH (2018)
Keyphrases
- endpoint detection
- speech signal
- speech processing
- speech recognition
- emotion recognition
- signal processing
- generative model
- social networks
- non stationary
- vocal tract
- network design
- text to speech
- network analysis
- audio visual
- heterogeneous networks
- automatic speech recognition
- noisy environments
- user interface
- neural network
- hidden markov models