Unsupervised Domain Discovery using Latent Dirichlet Allocation for Acoustic Modelling in Speech Recognition.
Mortaza DoulatyOscar SazThomas HainPublished in: CoRR (2015)
Keyphrases
- speech recognition
- latent dirichlet allocation
- topic modeling
- speech recognition systems
- topic models
- speaker independent
- topic discovery
- lda model
- speech recognizers
- generative model
- speech synthesis
- language model
- probabilistic topic models
- hidden markov models
- acoustic models
- automatic speech recognition
- hierarchical bayesian models
- speech signal
- noisy environments
- pattern recognition
- speech recognizer
- data mining
- acoustic features
- semi supervised
- text mining
- feature extraction
- neural network
- speaker identification
- text analysis
- knowledge discovery
- unsupervised learning
- text classification