Speaker recognition with two-step multi-modal deep cleansing.
Ruijie TaoKong Aik LeeZhan ShiHaizhou LiPublished in: CoRR (2022)
Keyphrases
- multi modal
- speaker recognition
- audio visual
- speaker verification
- gaussian mixture model
- vector quantization
- multi modality
- speech recognition
- probabilistic neural network
- high dimensional
- uni modal
- speaker identification
- image annotation
- video search
- speech signal
- model selection
- machine learning
- single modality
- neural network