Multi-Scale Aggregation Using Feature Pyramid Module for Text-Independent Speaker Verification.
Youngmoon JungSeong Min KyeYeunju ChoiMyunghun JungHoirin KimPublished in: CoRR (2020)
Keyphrases
- speaker verification
- multiscale
- scale space
- speaker recognition
- language identification
- image representation
- image features
- text mining
- noisy environments
- audio visual
- feature vectors
- information retrieval
- text data
- computer vision
- high dimensional
- object detection
- face recognition
- emotion recognition
- rank aggregation