WaveCRN: An Efficient Convolutional Recurrent Neural Network for End-to-End Speech Enhancement.
Tsun-An HsiehHsin-Min WangXugang LuYu TsaoPublished in: IEEE Signal Process. Lett. (2020)
Keyphrases
- end to end
- recurrent neural networks
- speech enhancement
- feed forward
- neural network
- noisy environments
- noise reduction
- recurrent networks
- artificial neural networks
- signal to noise ratio
- congestion control
- vocal tract
- hidden layer
- single channel
- network architecture
- speech signal
- linear prediction
- signal processing
- genetic algorithm
- non stationary
- linear combination