Web-Data Augmented Language Models for Mandarin Conversational Speech Recognition.
Tim NgMari OstendorfMei-Yuh HwangMan-Hung SiuIvan BulykoXin LeiPublished in: ICASSP (1) (2005)
Keyphrases
- speech recognition
- web data
- language model
- web mining
- language modeling
- speaker independent
- information retrieval
- document retrieval
- semi structured
- n gram
- probabilistic model
- speech synthesis
- multi modal
- web documents
- test collection
- retrieval model
- web pages
- automatic speech recognition
- web content
- link structure
- query terms
- vector space model
- speech signal
- noisy environments
- mixture model
- speech recognizer
- query logs
- query expansion
- document representation
- handwriting recognition
- speaker identification
- speech recognition systems
- word error rate
- search engine
- pattern recognition
- natural language
- web search engines