Online Speech Enhancement by Retraining of LSTM Using SURE Loss and Policy Iteration.
Sriharsha KoundinyaAbhijit KarmakarPublished in: Neural Process. Lett. (2021)
Keyphrases
- policy iteration
- speech enhancement
- markov decision processes
- noise reduction
- noisy environments
- reinforcement learning
- optimal policy
- markov decision process
- model free
- finite state
- signal to noise ratio
- fixed point
- least squares
- speech signal
- wiener filter
- single channel
- state space
- temporal difference
- average cost
- wavelet transform