Joint constraint algorithm based on deep neural network with dual outputs for single-channel speech separation

Single-channel speech separation (SCSS) plays an important role in speech processing. It is an underdetermined problem since several signals need to be recovered from one channel, which is more difficult to solve. To achieve SCSS more effectively, we propose a new cost function. What’s more, a joint...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:Signal, image and video processing Jg. 14; H. 7; S. 1387 - 1395
Hauptverfasser: Sun, Linhui, Zhu, Ge, Li, Pingan
Format: Journal Article
Sprache:Englisch
Veröffentlicht: London Springer London 01.10.2020
Springer Nature B.V
Schlagworte:
Algorithms
Artificial neural networks
Computer Imaging
Computer Science
Cost function
Image Processing and Computer Vision
Intelligibility
Model accuracy
Multimedia Information Systems
Original Paper
Pattern Recognition and Graphics
Separation
Signal processing
Signal,Image and Speech Processing
Speech
Speech processing
Vision
Dual outputs
Cost function
Single-channel speech separation
Joint constraint
Deep neural network (DNN)
ISSN:1863-1703, 1863-1711
Online-Zugang:Volltext
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
Beschreibung
Zusammenfassung:Single-channel speech separation (SCSS) plays an important role in speech processing. It is an underdetermined problem since several signals need to be recovered from one channel, which is more difficult to solve. To achieve SCSS more effectively, we propose a new cost function. What’s more, a joint constraint algorithm based on this function is used to separate mixed speech signals, which aims to separate two sources at the same time accurately. The joint constraint algorithm not only penalizes residual sum of square, but also exploits the joint relationship between the outputs to train the dual output DNN. In these joint constraints, the training accuracy of the separation model can be further increased. We evaluate the proposed algorithm performance on the GRID corpus. The experimental results show that the new algorithm can obtain better speech intelligibility compared to the basic cost function. In the aspects of source-to-distortion ratio , signal-to-interference ratio, source-to-artifact ratio and perceptual evaluation of speech quality, the novel approach can obtain better performance.
Bibliographie:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
ISSN:1863-1703
1863-1711
DOI:10.1007/s11760-020-01676-6