On Using Written Language Training Data for Spoken Language Modeling.
Richard M. SchwartzLong NguyenFrancis KubalaGeorge ChouGeorge ZavaliagkosJohn MakhoulPublished in: HLT (1994)
Keyphrases
- language modeling
- training data
- language model
- comparable corpora
- speech recognition
- retrieval model
- information retrieval
- query expansion
- probabilistic model
- n gram
- cross lingual
- relevance model
- document retrieval
- text classification
- training set
- natural language
- decision trees
- statistical language models
- data sets
- chinese text retrieval
- learning algorithm
- word segmentation
- sentence retrieval
- cross language information retrieval
- automatic speech recognition
- text mining
- test collection
- mixture model
- information retrieval systems
- context dependent
- classification accuracy
- statistical language modeling
- data mining