Collecting Colloquial and Spontaneous-like Sentences from Web Resources for Constructing Chinese Language Models of Speech Recognition.
Xinhui HuShigeki MatsudaChiori HoriHideki KashiokaPublished in: J. Inf. Process. (2013)
Keyphrases
- speech recognition
- web resources
- language model
- text summarization
- speech synthesis
- language modeling
- query expansion
- n gram
- document retrieval
- probabilistic model
- information retrieval
- speech signal
- word segmentation
- automatic speech recognition
- noun phrases
- learning resources
- web content
- handwriting recognition
- retrieval model
- test collection
- query terms
- mixture model
- natural language
- web pages
- word error rate
- natural language processing
- data mining
- hidden markov models
- relevance model
- sentence level
- translation model
- smoothing methods
- computer vision