scholarly journals Time-Frequency Masking: Linking Blind Source Separation and Robust Speech Recognition

10.5772/6382 ◽  
2008 ◽  
Author(s):  
Marco Khne ◽  
Roberto Togneri ◽  
Sven Nordholm
Keyword(s):  
Speech Recognition ◽  
Blind Source Separation ◽  
Source Separation ◽  
Robust Speech Recognition ◽  
Time Frequency

Perceptual evaluation of blind source separation for robust speech recognition

2008 ◽  
Vol 88 (10) ◽  
pp. 2578-2583 ◽  
Author(s):  
Leandro Di Persia ◽  
Diego Milone ◽  
Hugo Leonardo Rufiner ◽  
Masuzo Yanagida
Keyword(s):  
Speech Recognition ◽  
Blind Source Separation ◽  
Source Separation ◽  
Robust Speech Recognition ◽  
Perceptual Evaluation

scholarly journals An Underdetermined Blind Source Separation Method with Application to Modal Identification

2019 ◽  
Vol 2019 ◽  
pp. 1-15 ◽  
Author(s):  
Gang Yu
Keyword(s):  
Blind Source Separation ◽  
Source Separation ◽  
Modal Identification ◽  
Modal Parameters ◽  
Underdetermined Blind Source Separation ◽  
Structural Dynamic ◽  
Time Frequency ◽  
Modal Response ◽  
Experimental Validations ◽  
Straight Lines

In structural dynamic analysis, the blind source separation (BSS) technique has been accepted as one of the most effective ways for modal identification, in which how to extract the modal parameters using very limited sensors is a highly challenging task in this field. In this paper, we first review the drawbacks of the conventional BSS methods and then propose a novel underdetermined BSS method for addressing the modal identification with limited sensors. The proposed method is established on the clustering features of time-frequency (TF) transform of modal response signals. This study finds that the TF energy belonging to different monotone modals can cluster into distinct straight lines. Meanwhile, we provide the detailed theorem to explain the clustering features. Moreover, the TF coefficients of each modal are employed to reconstruct all monotone signals, which can benefit to individually identify the modal parameters. In experimental validations, two experimental validations demonstrate the effectiveness of the proposed method.

Mathematical view of a blind source separation on a time frequency space

2007 ◽  
Vol 187 (1) ◽  
pp. 153-162 ◽  
Author(s):  
Keiko Fujita ◽  
Yoshitsugu Takei ◽  
Akira Morimoto ◽  
Ryuichi Ashino
Keyword(s):  
Blind Source Separation ◽  
Source Separation ◽  
Frequency Space ◽  
Time Frequency
Sign in / Sign up

Export Citation Format

Share Document