Speech Dereverberation Based on Scale-Aware Mean Square Error Loss.
Luya QiangHao ShiMeng GeHaoran YinNan LiLongbiao WangSheng LiJianwu DangPublished in: ICONIP (5) (2021)
Keyphrases
- speech recognition
- speech signal
- recognition engine
- audio visual
- signal to noise ratio
- scale space
- information systems
- hidden markov models
- image quality
- social networks
- genetic algorithm
- machine learning
- neural network
- noisy environments
- error measure
- speaker identification
- speaker recognition
- speech synthesis
- real time