Interpreting Song Lyrics with an Audio-Informed Pre-trained Language Model.
Yixiao ZhangJunyan JiangGus XiaSimon DixonPublished in: ISMIR (2022)
Keyphrases
- language model
- audio features
- pre trained
- audio visual
- language modeling
- acoustic features
- low level
- training data
- music information retrieval
- visual features
- n gram
- control signals
- feature set
- music retrieval
- sound source
- query expansion
- speech recognition
- probabilistic model
- information retrieval
- training examples
- text data
- ad hoc information retrieval
- retrieval model
- mixture model
- multi modal
- visual information
- text classification
- multimedia
- visual tracking
- cross lingual
- speech signal
- relevance model
- image classification
- learning algorithm
- machine learning