Long-Form Speech Translation through Segmentation with Finite-State Decoding Constraints on Large Language Models.
Arya McCarthyHao ZhangShankar KumarFelix StahlbergKe WuPublished in: EMNLP (Findings) (2023)
Keyphrases
- finite state transducers
- language model
- language modeling
- finite state
- n gram
- speech recognition
- translation model
- word segmentation
- machine translation
- markov chain
- cross language retrieval
- probabilistic model
- language modelling
- retrieval model
- information retrieval
- out of vocabulary
- word error rate
- cross lingual
- query expansion
- statistical language models
- document retrieval
- model checking
- spoken term detection
- markov decision processes
- relevance model
- tree automata
- smoothing methods
- ad hoc information retrieval
- okapi bm
- test collection
- speech signal
- statistical language modeling
- context sensitive
- retrieval effectiveness
- language models for information retrieval
- vector space
- query terms
- vector space model
- document ranking
- query translation