Interpreting Song Lyrics with an Audio-Informed Pre-trained Language Model.
Yixiao ZhangJunyan JiangGus XiaSimon DixonPublished in: CoRR (2022)
Keyphrases
- language model
- audio features
- pre trained
- audio visual
- acoustic features
- language modeling
- training data
- low level
- visual features
- feature set
- probabilistic model
- music retrieval
- n gram
- music information retrieval
- training examples
- retrieval model
- control signals
- speech recognition
- information retrieval
- sound source
- mixture model
- query expansion
- smoothing methods
- ad hoc information retrieval
- text data
- translation model
- multi modal
- high dimensional
- pairwise
- visual data
- prior knowledge