Improving Keyword Recognition of Spoken Queries by Combining Multiple Speech Recognizer's Outputs for Speech-driven WEB Retrieval Task.
Masahiko MatsushitaHiromitsu NishizakiTakehito UtsuroSeiichi NakagawaPublished in: IEICE Trans. Inf. Syst. (2005)
Keyphrases
- speech recognizer
- combining multiple
- speech recognition
- spoken language
- speaker independent
- speech recognition systems
- broadcast news
- speech recognizers
- speaker dependent
- automatic speech recognition
- pattern recognition
- noisy environments
- query processing
- search queries
- web documents
- language model
- speaker identification
- hidden markov models
- acoustic models
- keywords
- language processing
- speech signal
- web pages
- dialogue system
- web search engines
- feature extraction
- semantic analysis
- information access
- natural language
- user queries
- semantic web
- linguistic knowledge
- query terms
- natural language processing
- video sequences
- speaker adaptation
- search engine