On DNN posterior probability combination in multi-stream speech recognition for reverberant environments.
Feifei XiongStefan GoetzeBernd T. MeyerPublished in: ICASSP (2017)
Keyphrases
- posterior probability
- speech recognition
- multi stream
- audio visual speech recognition
- speech signal
- hidden markov models
- bayesian networks
- audio visual
- generative model
- bayesian framework
- probability density function
- probabilistic model
- language model
- probability distribution
- automatic speech recognition
- noisy environments
- conditional probabilities
- multi modal
- speaker identification
- pattern recognition
- mixture model
- speech recognition systems