Using cross-decoder co-occurrences of phone n-grams in SVM-based phonotactic language recognition.
Mikel PeñagarikanoAmparo VaronaLuis Javier Rodríguez-FuentesGermán BordelPublished in: INTERSPEECH (2010)
Keyphrases
- co occurrence
- n gram
- language specific
- character n grams
- bag of words
- language model
- visual words
- viterbi algorithm
- wordnet
- variable length
- object recognition
- text classification
- semantic similarity
- feature extraction
- natural language
- language modeling
- language independent
- semantic relations
- named entities
- word segmentation
- action recognition
- topic models
- cross language information retrieval
- relevance feedback
- query terms
- part of speech
- semantic space
- word level
- web documents
- cross language
- retrieval model
- language identification
- out of vocabulary
- data mining
- inside outside algorithm