Phonetic analyses of word and segment variation using the TIMIT corpus of American english.
Patricia A. KeatingDani ByrdEdward FlemmingYuichi TodakaPublished in: Speech Commun. (1994)
Keyphrases
- word level
- english words
- statistical machine translation
- parallel corpus
- sentence pairs
- unknown words
- word sense
- sentence level
- multiword
- training corpus
- spoken document retrieval
- stop words
- machine translation
- english text
- language independent
- machine translation system
- hidden markov models
- word frequencies
- linguistic features
- link grammar
- spoken term detection
- cross lingual
- open domain
- word alignment
- n gram
- translation model
- broadcast news
- semantic roles
- cross language
- parallel corpora
- speaker verification
- speech recognition
- word pairs
- document level
- speech corpus
- word sense disambiguation
- query translation
- broad coverage
- person names
- document images
- text classification
- chinese english
- linguistic information
- co occurrence
- text corpus
- tf idf
- cross language information retrieval
- wordnet
- sentiment analysis
- word recognition
- language specific
- word segmentation
- noun phrases
- document analysis
- natural language text
- language model
- natural language
- ambiguous words
- comparable corpora
- bilingual dictionaries
- part of speech
- target language