AudioPaLM: A Large Language Model That Can Speak and Listen.
Paul K. RubensteinChulayuth AsawaroengchaiDuc Dung NguyenAnkur BapnaZalán BorsosFélix de Chaumont QuitryPeter ChenDalia El BadawyWei HanEugene KharitonovHannah MuckenhirnDirk PadfieldJames QinDanny RozenbergTara N. SainathJohan SchalkwykMatthew SharifiMichelle Tadmor RamanovichMarco TagliasacchiAlexandru TudorMihajlo VelimirovicDamien VincentJiahui YuYongqiang WangVicky ZayatsNeil ZeghidourYu ZhangZhishuai ZhangLukas ZilkaChristian Havnø FrankPublished in: CoRR (2023)
Keyphrases
- language model
- language modeling
- n gram
- language modelling
- probabilistic model
- information retrieval
- speech recognition
- document retrieval
- query expansion
- mixture model
- test collection
- context sensitive
- ad hoc information retrieval
- pseudo relevance feedback
- vector space model
- statistical language models
- retrieval model
- query specific
- smoothing methods
- query terms
- translation model
- term weighting
- relevance model
- document ranking
- information retrieval systems
- word error rate
- inter document similarities
- keywords