SavedAdd your journal

Journals / Avrupa Bilim ve Teknoloji Dergisi / 2020 / Ejosat Özel Sayı 2020 (ARACONF)

Performance Analysis of Blind Source Algorithms in the Separation of Sound Signals

Ses İşaretlerinin Ayrıştırılmasında Kör Kaynak Algoritmalarının Performans Analizleri

Hüsamettin ÇELİK
Nurhan KARABOĞA
Pages
399–404
Publication Date
2020-04-01
DOI
—
🏛️Bibliographic metadata and full text access for this article are provided via DergiPark.
DergiPark Record ↗
✨

AI Summary & Key Takeaways

AI Insight
⚡ TL;DR(Too Long; Didn't Read)

It has been evaluated according to performance rates and processing times by considering the performance analysis of the algorithms.

📌 3 Key Takeaways

🎯
Objective & Hypothesis:Obtaining a mixture of two or more sounds or separating the sounds recorded in the noisy environment from noise is among the most studied topic.
📊
Key Findings & Data:Since noise type, source and mixing environments of sounds are unknown, the processing time and performance of the algorithms used in the separation process differ.
💡
Conclusion & Impact:It has been evaluated according to performance rates and processing times by considering the performance analysis of the algorithms.
🔬Design:Research Article
📍Scope:Comprehensive Sample
⚙️Variables:Kör kaynak ayırma · ICA · PICA

Abstract

Obtaining a mixture of two or more sounds or separating the sounds recorded in the noisy environment from noise is among the most studied topic. Since noise type, source and mixing environments of sounds are unknown, the processing time and performance of the algorithms used in the separation process differ. Blind source algorithms are used to decompose mixed signs. From the data set consisting of linear mixed signal sources, the process of estimating the signals or noise separately is expressed as blind source decomposition. Although there are many methods in engineering applications, it is necessary to analyze which algorithm will be more suitable considering the design constraints and requirements. In this study, as three different methods; Pearson independent component analysis (PICA), Second order blind identification (SOBI) algorithm and Joint approximate diagonalization of eigen matrices (JADE) algorithms were compared. It has been evaluated according to performance rates and processing times by considering the performance analysis of the algorithms.

Özet

İki veya daha fazla sesin karışımından birini elde etmek veya gürültülü ortamda kaydedilen seslerin gürültüden ayrıştırılması her zaman popülerliğini korumaktadır. Gürültü çeşidi, kaynağı ve seslerin karışım ortamları bilinmediği için ayrıştırma işleminde kullanılan algoritmaların işlem süresi ve performansları farklılık göstermektedir. Karışmış işaretleri ayrıştırmada kör kaynak algoritmaları kullanılmaktadır. Doğrusal karışmış işaret kaynaklarından oluşan veri kümesinden, işaretlerin veya gürültünün ayrı ayrı tahmin edilme işlemi kör kaynak ayrıştırma olarak ifade edilmektedir. Mühendislik uygulamalarında birçok yöntem olsa da tasarım kısıtlamaları ve gereksinimleri göz önüne alındığında hangi algoritmanın daha uygun olacağını analiz etmek gerekir. Bu çalışmada üç farklı yöntem olarak; Pearson bağımsız bileşen analizi (Pearson Independent Component Analysis -PICA), İkinci dereceden kör tanımlama ( Second-Order Blind Identification-SOBİ) algoritması ve Ortak yaklaşım özdeğerlerin köşegenleştirilmesi (Joint Approximation Diagonalization of Eigen-matrices-JADE) algoritmaları karşılaştırılmıştır. Algoritmaların performans analizleri dikkate alınarak başarım oranları ve işlem sürelerine göre değerlendirilmiştir.

🔖

Cite This Article

ÇELİK, H., KARABOĞA, N. (2020). Performance Analysis of Blind Source Algorithms in the Separation of Sound Signals. Avrupa Bilim ve Teknoloji Dergisi, Ejosat Özel Sayı 2020 (ARACONF), 399–404. https://ajindex.com/articles/471779

📄 Full Text PDF Viewer

📄

PDF görüntüleyici hazırlanıyor...

References (9)

  1. Bach, F. R., & Jordan, M. I. (2002). Kernel independent component analysis. (s. 1-48). Journal of machine learning research. Belouchrani, A., Abed-Meraim, K., Cardoso, J. -F., & Moulines, E. (1993). Second-order blind separation of temporally correlated sources. In Proc. Int. Conf. Digital Signal Processing, (s. 346-351).
  2. Citeseer. Belouchrani, A., Abed-Meraim, K., Cardoso, J. -F., & Moulines, E. (1997). A blind source separation technique using second-order statistics. IEEE Transactions on Signal Processing, (s. 434-444).
  3. Bronkhorst, A. W. (2000). The cocktail party phenomenon: A review on speech intelligibility in multiple-talker conditions. (s. 117-128). Acta Acustica united with Acustica. Cardoso, J. F., & Souloumiac, A. (1993). Blind beamforming for non-Gaussian signals. IEE proceedings F (radar and signal processing) (s. 362-370).
  4. IET Digital Library. Celik, H., Ilgin, F. Y., & Sevim, Y. (2019). Müzik işaretlerin tek kanal kör kaynak ayrıştırma ile ayrıştırılması. (s. 26-38). NWSA Engineering Sciences. Hyvärinen, A. (1984). Independent component analysis: recent advances. Philosophical Transactions of the Royal Society A: Mathematical, Physical and Engineering Sciences, (s. 371). Hyvärinen, A., & Oja, E. (2000). Independent component analysis: algorithms and applications. (s. 411-430).
  5. Neural networks. Ilgin, F. Y., Celik, H., & Sevim, Y. (2012). Stable signal separation algorithm for ECG signals. 2012 International Symposium on Innovations in Intelligent Systems and Applications (s. 1-4).
  6. IEEE. Karvanen, J., Eriksson, J., & Koivunen, V. (2000). Pearson system based method for blind separation. Proceedings of Second International Workshop on Independent Component Analysis and Blind Signal Separation (ICA2000), (s. 585-590).
  7. Helsinki, Finland. Kato, H., Nagahara, Y., Araki, S., Sawada, H., & Makino, S. (2006). Parametric-Pearson-based independent component analysis for frequency-domain blind speech separation. 14th European Signal Processing Conference, (s. 1-5).
  8. Florence. Liu, X., Wang, H., Huang, M., & Yang, W. (2019). An improved second-order blind identification (SOBI) signal de-noising method for dynamic deflection measurements of bridges using ground-based synthetic aperture radar (GBSAR). Applied Sciences, (s. 3561-3561).
  9. Miettinen, J., Nordhausen, K., & Taskinen, S. (2017). Blind source separation based on joint diagonalization in R: The packages JADE and BSSasymp. Journal of Statistical Software. Rainieri, C. (2014). Perspectives of second-or