Speech enhancement using a DNN-augmented colored-noise Kalman filter

•Colored-noise Kalman filter is adopted in our system, which is more component to deal with the complex noise and alleviate the speech distortion.•A multi-objective DNN is first employed to joint estimate parameters of the clean speech autoregressive (AR) model and the noise AR model. Two kinds of D...

Ausführliche Beschreibung

Gespeichert in:

Bibliographische Detailangaben
Veröffentlicht in:	Speech communication 2020-12, Vol.125, p.142-151
Hauptverfasser:	Yu, Hongjiang, Zhu, Wei-Ping, Champagne, Benoit
Format:	Artikel
Sprache:	eng
Schlagworte:	Acoustic mapping Algorithms Artificial neural networks Autoregressive models Autoregressive processes Corlored-noise Kalman filter Deep neural network Denoising Kalman filters Linear prediction Noise Noise reduction Optimization Parameter estimation Process parameters Spectral subtraction Speech Speech enhancement Speech processing Subtraction
Online-Zugang:	Volltext
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!

Schreiben Sie den ersten Kommentar!