Toward Joint Language Modeling for Speech Units and Text.
Ju-Chieh ChouChung-Ming ChienWei-Ning HsuKaren LivescuArun BabuAlexis ConneauAlexei BaevskiMichael AuliPublished in: EMNLP (Findings) (2023)
Keyphrases
- language modeling
- language model
- information retrieval
- speech recognition
- retrieval model
- finite state transducers
- text retrieval
- query expansion
- n gram
- cross lingual
- probabilistic model
- word error rate
- text classification
- anchor text
- keywords
- statistical language models
- text documents
- text mining
- document retrieval
- test collection
- information retrieval systems
- word segmentation
- feature extraction
- improvements in retrieval effectiveness
- statistical language modeling
- data mining
- mixture model
- translation model
- multiword
- search engine