Two-Stage Deep Learning for Noisy-Reverberant Speech Enhancement.
Yan ZhaoZhong-Qiu WangDeLiang WangPublished in: IEEE ACM Trans. Audio Speech Lang. Process. (2019)
Keyphrases
- deep learning
- speech enhancement
- noisy environments
- speech signal
- speech recognition
- unsupervised learning
- noise reduction
- background noise
- machine learning
- vocal tract
- automatic speech recognition
- linear prediction
- mental models
- non stationary
- signal to noise ratio
- additive noise
- weakly supervised
- hidden markov models
- bayesian networks
- single channel
- image processing
- object recognition
- multiscale
- maximum likelihood
- super resolution
- text classification
- higher order
- supervised learning
- d objects