Full Bayesian Hidden Markov Model Variational Autoencoder for Acoustic Unit Discovery.
Thomas GlarnerPatrick HanebrinkJanek EbbersReinhold Haeb-UmbachPublished in: INTERSPEECH (2018)
Keyphrases
- hidden markov models
- speaker independent
- speech recognition
- markov models
- noisy speech
- bayesian networks
- gesture recognition
- sequential data
- markov model
- image segmentation
- handwritten word recognition
- conditional random fields
- viterbi algorithm
- visual speech
- continuous hidden markov models
- speech recognition systems
- hidden state
- posterior probability
- maximum likelihood
- hidden states
- baum welch
- automatic speech recognition
- bayesian inference
- pattern discovery