A Deep Learning Loss Function based on Auditory Power Compression for Speech Enhancement.
Tianrui WangWeibin ZhuPublished in: CoRR (2021)
Keyphrases
- loss function
- deep learning
- speech enhancement
- noisy environments
- pairwise
- noise reduction
- signal to noise ratio
- unsupervised learning
- support vector
- image compression
- machine learning
- single channel
- speech signal
- mental models
- signal processing
- visual information
- compression ratio
- weakly supervised
- pattern recognition
- reinforcement learning