A Novel Encoder-Decoder Model via NS-LSTM Used for Bone-Conducted Speech Enhancement
A Novel Encoder-Decoder Model via NS-LSTM Used for Bone-Conducted Speech Enhancement is a scholarly work, published in 2018 in ''IEEE Access''. The main subjects of the publication include non-negative matrix factorization, recurrent neural network, artificial intelligence, decoding method, computer science, artificial neural network, Speech enhancement, encoder, speech recognition, matrix decomposition, audio signal processing, speech coding, pattern recognition, and Sparse modeling. Objective and subjective results demonstrate that the method behaves better and achieves satisfactory performance even when coping with some challenging cases.