Improving HMM/DNN in ASR of under-resourced languages using probabilistic sampling.
Meixu SongQingqing ZhangJielin PanYonghong YanPublished in: ChinaSIP (2015)
Keyphrases
- automatic speech recognition
- hidden markov models
- speech recognition
- probabilistic model
- speech signal
- generative model
- expressive power
- databases
- noisy environments
- uncertain data
- multi lingual
- language identification
- random sampling
- training process
- context sensitive
- language independent
- monte carlo
- neural network
- sampling algorithm
- text classification
- information retrieval