Extraction of Noise-Robust Speaker Embedding Based on Generative Adversarial Networks.
Jianfeng ZhouTao JiangQingyang HongLin LiPublished in: APSIPA (2019)
Keyphrases
- image noise
- greater robustness
- watermark extraction
- information extraction
- geometric distortions
- social networks
- imaging artifacts
- random noise
- noisy environments
- speech recognition
- computationally efficient
- feature extraction
- image processing
- noisy data
- noise reduction
- noise level
- audio visual
- missing data
- generative model
- bayesian networks
- robust statistical
- neural network