Audio Captioning using Pre-Trained Large-Scale Language Model Guided by Audio-based Similar Caption Retrieval.
Yuma KoizumiYasunori OhishiDaisuke NiizumiDaiki TakeuchiMasahiro YasudaPublished in: CoRR (2020)
Keyphrases
- language model
- retrieval model
- document retrieval
- test collection
- information retrieval
- ad hoc information retrieval
- language modeling
- query expansion
- pre trained
- smoothing methods
- n gram
- language models for information retrieval
- multimedia
- speech recognition
- query terms
- relevance model
- mixture model
- query specific
- visual information
- probabilistic model
- audio visual
- image retrieval
- multi modal
- document collections
- document length
- relevant documents
- data points
- training set
- pseudo relevance feedback
- bayesian networks
- unsupervised learning
- feature selection
- machine learning