Robustness of LSTM Neural Networks for the Enhancement of Spectral Parameters in Noisy Speech Signals.
Marvin Coto-JiménezPublished in: MICAI (2) (2018)
Keyphrases
- speech signal
- neural network
- noisy environments
- linear prediction
- spectral analysis
- speech recognition
- recurrent neural networks
- automatic speech recognition
- maximum likelihood
- pattern recognition
- speech enhancement
- image enhancement
- background noise
- blind source separation
- spectral subtraction
- hidden markov models
- automatic speech recognition systems
- sound source
- autoregressive
- additive noise
- noise reduction
- noisy images
- feed forward
- back propagation
- image processing