Unsupervised cross-adaptation using language model and deep learning based acoustic model adaptations.
Akira TakagiKazuki KonnoMasaharu KatoTetsuo KosakaPublished in: APSIPA (2014)
Keyphrases
- language model
- deep learning
- unsupervised learning
- deep architectures
- weakly supervised
- language modeling
- n gram
- probabilistic model
- information retrieval
- speech recognition
- supervised learning
- semi supervised
- mixture model
- machine learning
- query expansion
- ad hoc information retrieval
- retrieval model
- smoothing methods
- object class
- feature selection
- model selection
- domain specific
- dimensionality reduction
- natural language
- multiscale
- relation extraction
- bayesian networks
- translation model
- data mining