A Reverberation-Time-Aware Approach to Speech Dereverberation Based on Deep Neural Networks

A reverberation-time-aware deep-neural-network (DNN)-based speech dereverberation framework is proposed to handle a wide range of reverberation times. There are three key steps in designing a robust system. First, in contrast to sigmoid activation and min-max normalization in state-of-the-art algori...

Ausführliche Beschreibung

Gespeichert in:

Bibliographische Detailangaben
Veröffentlicht in:	IEEE/ACM transactions on audio, speech, and language processing Jg. 25; H. 1; S. 102 - 111
Hauptverfasser:	Wu, Bo, Li, Kehuang, Yang, Minglei, Lee, Chin-Hui
Format:	Journal Article
Sprache:	Englisch
Veröffentlicht:	Piscataway IEEE 01.01.2017 The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
Schlagworte:	Acoustic context Activation Artificial neural networks Context deep neural networks (DNNs) Feature extraction frame shift linear output layer mean-variance normalization Reverberation Reverberation time reverberation-time-aware (RTA) Speech speech dereverberation Speech processing Training
ISSN:	2329-9290, 2329-9304
Online-Zugang:	Volltext
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!

Schreiben Sie den ersten Kommentar!