Two-step correction of speech recognition errors based on n-gram and long contextual information.
Ryohei NakataniTetsuya TakiguchiYasuo ArikiPublished in: INTERSPEECH (2013)
Keyphrases
- contextual information
- n gram
- speech recognition errors
- language model
- context aware
- speech recognition
- spoken document retrieval
- text classification
- bag of words
- language modeling
- language independent
- out of vocabulary
- high level
- viterbi algorithm
- contextual knowledge
- word segmentation
- part of speech
- information extraction
- image classification
- information retrieval
- document retrieval