Collecting Colloquial and Spontaneous-like Sentences from Web Resources for Constructing Chinese Language Models of Speech Recognition.
Xinhui HuShigeki MatsudaChori HoriHideki KashiokaPublished in: Inf. Media Technol. (2013)
Keyphrases
- speech recognition
- web resources
- language model
- text summarization
- language modeling
- speech synthesis
- n gram
- query expansion
- document retrieval
- information retrieval
- probabilistic model
- learning resources
- automatic speech recognition
- word segmentation
- retrieval model
- test collection
- mixture model
- speech signal
- web pages
- noun phrases
- natural language
- web content
- relevance model
- sentence level
- handwriting recognition
- translation model
- named entity recognition
- question answering
- query terms
- word error rate