Speech Enhancement with LSTM Recurrent Neural Networks and its Application to Noise-Robust ASR.
Felix WeningerHakan ErdoganShinji WatanabeEmmanuel VincentJonathan Le RouxJohn R. HersheyBjörn W. SchullerPublished in: LVA/ICA (2015)
Keyphrases
- recurrent neural networks
- noisy environments
- speech enhancement
- noise reduction
- speech recognition
- long short term memory
- speech signal
- automatic speech recognition
- neural network
- background noise
- recurrent networks
- noisy speech
- feed forward
- echo state networks
- signal to noise ratio
- artificial neural networks
- image processing
- linear prediction
- learning algorithm
- machine learning