DNN-based speech enhancement with self-attention on feature dimension.
Jiaming ChengRuiyu LiangLi ZhaoPublished in: Multim. Tools Appl. (2020)
Keyphrases
- speech enhancement
- feature dimension
- noisy environments
- noise reduction
- signal to noise ratio
- single channel
- speech signal
- support vector machine
- machine learning
- linear prediction
- pattern recognition
- non stationary
- vocal tract
- relevance feedback
- focus of attention
- multiresolution
- background noise
- wiener filter
- smoothing algorithm
- face recognition
- decision trees