A Deep Generative Model of Vowel Formant Typology.
Ryan CotterellJason EisnerPublished in: CoRR (2018)
Keyphrases
- generative model
- speech signal
- vocal tract
- speech recognition
- probabilistic model
- speech synthesis
- mixture model
- bayesian framework
- posterior probability
- discriminative learning
- conditional random fields
- semi supervised
- topic models
- latent dirichlet allocation
- prior knowledge
- feature representations
- automatic speech recognition
- speaker independent
- text classification
- markov chain monte carlo
- hidden markov models
- bayesian networks
- discriminative models
- video representation
- high level
- image processing
- computer vision