Transformer-based Sequence Labeling for Audio Classification based on MFCCs.
C. S. SonaliChinmayi B. SAhana BalasubramanianPublished in: CoRR (2023)
Keyphrases
- sequence labeling
- classification accuracy
- text classification
- hedge detection
- conditional random fields
- speech recognition
- pattern recognition
- support vector machine
- decision trees
- feature vectors
- feature extraction
- audio features
- support vector
- image classification
- feature selection
- dependency parsing
- training samples
- pattern classification
- supervised learning
- non stationary
- document classification
- audio visual
- language model
- training set