Few-Shot Keyword Spotting from Mixed Speech.
Junming YuanYing ShiLantian LiDong WangAskar HamdullaPublished in: CoRR (2024)
Keyphrases
- keyword spotting
- speech recognition
- speech processing
- hidden markov models
- speech signal
- printed documents
- signal processing
- video sequences
- handwritten documents
- language model
- pattern recognition
- speaker identification
- automatic speech recognition
- video data
- video shots
- noisy environments
- news video
- video content
- key frames
- visual features
- digital libraries