Text-Style Conversion of Speech Transcript into Web Document for Lecture Archive.
Masashi ItoTomohiro OhnoShigeki MatsubaraPublished in: J. Adv. Comput. Intell. Intell. Informatics (2009)
Keyphrases
- web documents
- textual information
- information extraction
- keywords
- speech recognition
- semi structured
- web pages
- prefetching
- html documents
- text to speech synthesis
- vector space model
- web content
- n gram
- unstructured documents
- metadata
- information retrieval
- writing style
- text recognition
- text to speech
- speech signal
- text mining
- xml documents
- hidden markov models
- knowledge discovery
- multi lingual
- web data
- natural language processing
- authorship attribution
- lexical features
- visual features