MFA: TDNN with Multi-Scale Frequency-Channel Attention for Text-Independent Speaker Verification with Short Utterances.
Tianchi LiuRohan Kumar DasKong Aik LeeHaizhou LiPublished in: ICASSP (2022)
Keyphrases
- speaker verification
- multiscale
- noisy environments
- speaker recognition
- audio visual
- prosodic features
- language identification
- emotion recognition
- multilayer perceptron
- information retrieval
- keywords
- text mining
- semantic information
- using artificial neural networks
- dimensionality reduction
- video sequences
- image sequences
- computer vision