Hidden Semi-Markov Model Based Speech Recognition System using Weighted Finite-State Transducer.
Keiichiro OuraHeiga ZenYoshihiko NankakuAkinobu LeeKeiichi TokudaPublished in: ICASSP (1) (2006)
Keyphrases
- semi markov
- finite state transducers
- finite state
- machine translation
- n gram
- language modeling
- edit distance
- grammatical inference
- conditional random fields
- hidden markov models
- markov decision processes
- statistical pattern recognition
- language model
- markov chain
- speech recognition
- object recognition
- pattern recognition
- machine learning
- pattern matching
- prior knowledge
- multimedia