Inference skipping for more efficient real-time speech enhancement with parallel RNNs

Deep neural network (DNN) based speech enhancement models have attracted extensive attention due to their promising performance. However, it is difficult to deploy a powerful DNN in real-time applications because of its high computational cost. Typical compression methods such as pruning and quantiz...

Ausführliche Beschreibung

Bibliographische Detailangaben

Veröffentlicht in:	arXiv.org 2022-07
Hauptverfasser:	Le, Xiaohuai, Tong, Lei, Chen, Kai, Lu, Jing
Format:	Artikel
Sprache:	eng
Schlagworte:	Artificial neural networks Business competition Computer Science - Sound Computing costs Pruning Real time Recurrent neural networks Speech processing Strategy Voice activity detectors Voice recognition
Online-Zugang:	Volltext
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!