Abstract
In this paper we present a novel hybrid algorithm for blind source separation of three speech signals in a real room environment. The algorithm in addition to using second-order statistics also exploits an information-theoretic approach, based on higher order statistics, to achieve source separation and is well suited for real-time implementation due to its fast adaptive methodology. It does not require any prior information or parameter estimation. The algorithm also uses a novel post-separation speech harmonic alignment that results in an improved performance. Experimental results in simulated and real environments verify the effectiveness of the proposed method, and analysis demonstrates that the algorithm is computationally efficient.
Highlights
1 Introduction The blind source separation (BSS) of speech signals known as convolutive BSS is a very challenging problem in real room environments
These direction of arrival (DOA)-based algorithms are more semi-blind in nature than blind itself since they are dependent on certain geometrical arrangement
The frequency domain implementation will have two types of latencies in the algorithm: the first will be the computational latency calculated from the million multiplicationaccumulations (MMACS) of the algorithm divided by the MMACS capacity of the digital signal processor and the second is the time it takes to fill up the block for the fast Fourier transform (FFT)
Summary
The blind source separation (BSS) of speech signals known as convolutive BSS is a very challenging problem in real room environments. The room reverberation value is taken to be 0.6 with a room impulse response length of 100 ms For this reason, longer speech results (40 s) have been shown to verify the convergence of the algorithm to its true minimum and obtaining the true separation filters. It was less than the performance in the simulated environment discussed above. It is pertinent to mention here that the hybrid algorithm along with harmonic alignment only performs blind source separation and does not carry out any equalisation on the separated streams
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have