Long-Form Speech Translation through Segmentation with Finite-State Decoding Constraints on Large Language Models.
Arya D. McCarthyHao ZhangShankar KumarFelix StahlbergKe WuPublished in: CoRR (2023)
Keyphrases
- finite state transducers
- language model
- language modeling
- finite state
- n gram
- speech recognition
- word segmentation
- translation model
- retrieval model
- markov chain
- probabilistic model
- cross language retrieval
- information retrieval
- cross lingual
- machine translation
- document retrieval
- query expansion
- word error rate
- language modelling
- statistical language models
- smoothing methods
- tree automata
- context sensitive
- test collection
- out of vocabulary
- vector space model
- text classification
- language models for information retrieval
- spoken term detection
- model checking
- multiword
- relevance model
- pseudo relevance feedback
- data mining
- optimal policy
- sufficient conditions
- ad hoc information retrieval
- statistical language modeling