Tensor-Train Long Short-Term Memory for Monaural Speech Enhancement.
Suman SamuiIndrajit ChakrabartiSoumya K. GhoshPublished in: CoRR (2018)
Keyphrases
- speech enhancement
- noisy environments
- noise reduction
- signal to noise ratio
- single channel
- speech signal
- linear prediction
- recurrent neural networks
- background noise
- multi channel
- wiener filter
- higher order
- vocal tract
- additive noise
- automatic speech recognition
- smoothing algorithm
- edge preserving
- machine learning
- autoregressive
- independent component analysis
- speech recognition
- multiscale