RPCA-based Real-time Speech and Music Separation Method

Akbar ranjbar | Aminollah Mahabadi | Mohaddeseh Mirbeygi

---

URL :   http://research.shahed.ac.ir/WSR/WebPages/Report/PaperView.aspx?PaperID=148096
Date :  2021/02/05
Publish in :    Speech Communication
DOI :  https://doi.org/10.1016/j.specom.2020.12.003
Link :  https://www.sciencedirect.com/science/article/pii/S0167639320303071
Keywords :Robust Principal Component Analysis (RPCA) Randomized singular value decomposition (RSVD) Bilateral Random Projection (BRP) Automatic speech and music separation Embedded real-time system

Abstract :

---

The improvement of the performance of online separating speech and music is an 𝑁𝑃 problem and the separation optimization increases the complexity of the method in a Robust Principal Component Analysis (RPCA) method which is time consuming in big size matrix computations. This paper presents a RPCA-based speech and music separation method to reduce the amount of computational complexity and be robust to artificial noise by proposing two novel algorithms. The key idea of our real-time method is designing a novel random singular value decomposition algorithm in a non-convex optimization environment to significantly decrease the complexity of previous RPCA methods from 𝑚𝑖𝑛(𝑚𝑛22 , 𝑚𝑛) 𝑓𝑙𝑜𝑝𝑠 to 𝑚𝑛𝑟 𝑓𝑙𝑜𝑝𝑠 where 𝑟 ≪ 𝑚𝑖𝑛(𝑚, 𝑛) to obtain better performance and get qualified results. Experimental results of different datasets compared with the best state-of-the-art method show that the proposed method is more reliable and achieves an average 339 speedup by the significant reduction of computational complexity, increases the quality of the speech signal by 295, improves the quality of the music signal by 244 and the robustness of artificial noise without needing any learning technique or requiring particular features .