Embedding Encoder-Decoder With Attention Mechanism for Monaural Speech Enhancement

The auditory selection framework with attention and memory (ASAM), which has an attention mechanism, embedding generator, generated embedding array, and life-long memory, is used to deal with mixed speech. When ASAM is applied to speech enhancement, the discrepancy between the voice and noise featur...

Ausführliche Beschreibung

Bibliografische Detailangaben

Hauptverfasser:	Tian Lan, Wenzheng Ye, Yilan Lyu, Junyi Zhang, Qiao Liu
Format:	Artigo
Sprache:	Inglês
Veröffentlicht:	IEEE 2020-01-01
Schriftenreihe:	IEEE Access
Schlagworte:	Speech enhancement embedding encoder-decoder convolutional neural network attention mechanism neural network
Online-Zugang:	https://ieeexplore.ieee.org/document/9095322/
Tags:	Tag hinzufügen Keine Tags, Fügen Sie das erste Tag hinzu!