Title :
Blind audio source separation by NTF and its perceptual quality evaluation
Author :
M. Altug Keyder;Bilge Gunsel
Author_Institution :
?o?ulortam ??aret ??leme ve ?r?nt? Tanima Lab. Elektronik ve Haberle?me M?hendisli?i B?l?m?, ?stanbul Teknik ?niversitesi 34469 Maslak, Turkey
fDate :
4/1/2008 12:00:00 AM
Abstract :
In this paper, the audio blind source separation (BSS) using three dimensional nonnegative tensor factorization (3D-NTF), is realized. The audio source separation is modeled as an optimization problem and the beta-divergence cost function is iteratively optimized by alternating multiplicative update rules. The traditional measures which are used to evaluate the decomposition performance are known to be not informative about perceptual quality of the audio signals. Therefore performance of the designed system is evaluated not only with the well known Amari index, but also with perceptual audio quality criterions which are defined in the recommendation report, ITU-R BS.1387 of International Telecommunication Union (ITU). In this study, it has been shown that source decomposition performance of the NTF modelling on audio data mixed under different conditions, is superior to the nonnegative matrix factorization (NMF). Furthermore, it has been observed that some of the decomposed sources are acceptable according to Amari index while thay are not with respect to the perceptual quality criteria thus it can be concluded that the perceptual criteria is more suitable to objective quality evaluation of audio.
Keywords :
"Artificial neural networks","Communications technology","Source separation","Signal processing","Distortion measurement","Blind source separation","Indexes"
Conference_Titel :
Signal Processing, Communication and Applications Conference, 2008. SIU 2008. IEEE 16th
Print_ISBN :
978-1-4244-1998-2
DOI :
10.1109/SIU.2008.4632692