New automatic forward and backward blind sources separation algorithms for noise reduction and speech enhancement

• We propose two new automatic VAD algorithms of types forward and backward BSS.
• The cross-adaptive filters are adapted automatically thanks to the proposed techniques.
• The proposed automatic algorithms are used to separate speech form noise and therefore enhance the speech signal intelligibility.
• The proposed algorithms show very good performances even in very noisy conditions.

In this paper, we consider the speech enhancement problem in a moving car through a blind source separation (BSS) scheme involving two spaced microphones. The forward and backward blind source separation structures often use manual voice activity detector (MVAD) systems to control the adaptation of the separating adaptive filters. In this paper, we propose two new automatic voice activity detector (AVAD) systems that allow adapting the original forward and backward BSS structures automatically. The proposed AVAD systems are based on the use of the forward BSS structure to estimate the optimal values of the separating adaptive filters step-sizes. Moreover, the new proposed algorithms are stable and could be used even in very noisy conditions. Intensive experiments are carried out with these two new proposed algorithms to validate their good performances in speech enhancement and noise reduction applications. The presented experiments are based on the system mismatch, the cepstral distance and the output signal-to-noise ratio criteria evaluations. The obtained results show the good performances of the proposed algorithms in comparison with their original versions, where manual VAD systems are used.

Figure optionsDownload as PowerPoint slide