Wav2sv: End-to-end Speaker Embeddings Learning from Raw Waveforms based on Metric Learning for Speaker Verification.
Zhiqing ChenYifan PanHaoran ZhangYuesheng ZhuPublished in: ITCC (2022)
Keyphrases
- support vector
- end to end
- speaker verification
- metric learning
- learning tasks
- distance metric learning
- support vector machine
- distance metric
- speaker recognition
- feature selection
- supervised learning
- computer vision
- multi task
- learning process
- neural network
- unsupervised learning
- principal component analysis
- active learning
- pairwise
- audio visual
- pattern recognition
- reinforcement learning