Toward Joint Language Modeling for Speech Units and Text.
Ju-Chieh ChouChung-Ming ChienWei-Ning HsuKaren LivescuArun BabuAlexis ConneauAlexei BaevskiMichael AuliPublished in: CoRR (2023)
Keyphrases
- language modeling
- information retrieval
- language model
- retrieval model
- speech recognition
- finite state transducers
- query expansion
- text retrieval
- cross lingual
- probabilistic model
- word error rate
- n gram
- document retrieval
- improvements in retrieval effectiveness
- anchor text
- text documents
- text classification
- speech signal
- statistical language models
- information retrieval systems
- automatic speech recognition
- text mining
- machine translation system
- document analysis
- vector space model
- web documents
- test collection
- information extraction
- word pairs
- dimensionality reduction
- query terms
- machine learning