This research focuses on the development of speech enhancement techniques for two-channel audio systems. Specifically, we explore the utilization of an efficient sparseness recursive algorithm to tackle this challenge. The algorithm is designed to identify and attenuate noise components present in the audio signals, with the aim of improving the overall audio quality. In this investigation, we propose innovative approaches and enhancements to the sparseness recursive normalized least mean square (NLMS) algorithm, denoted Backward µ-law Proportionate NLMS (BMPNLMS), making it more suitable and effective for two-channel speech enhancement. By capitalizing on the sparsity properties of the audio signals, techniques proposed in this paper aim to enhance the desired audio while suppressing unwanted noise. Performance of the presented algorithm was examined by rigorous experiments based on several criteria. The obtained results thoroughly confirm the effectiveness of the proposed approach in real-world situations.
Key words: Backward µ-law proportionate algorithm; Backward normalized least mean square algorithm; Signal to noise ratio; Cepstral distance; System mismatch; Speech signal.
|
