Biblio

Speech enhancement is often applied for speech-based systems due to the proneness of speech signals to additive background noise. While speech processing-based methods are traditionally used for speech enhancement, with advancements in deep learning technologies, many efforts have been made to implement them for speech enhancement. Using deep learning, the networks learn mapping functions from noisy data to clean ones and then learn to reconstruct the clean speech signals. As a consequence, deep learning methods can reduce what is so-called musical noise that is often found in traditional speech enhancement methods. Currently, one popular deep learning architecture for speech enhancement is generative adversarial networks (GAN). However, the cross-entropy loss that is employed in GAN often causes the training to be unstable. So, in many implementations of GAN, the cross-entropy loss is replaced with the least-square loss. In this paper, to improve the training stability of GAN using cross-entropy loss, we propose to use deep regret analytic generative adversarial networks (Dragan) for speech enhancements. It is based on applying a gradient penalty on cross-entropy loss. We also employ relativistic rules to stabilize the training of GAN. Then, we applied it to the least square and Dragan losses. Our experiments suggest that the proposed method improve the quality of speech better than the least-square loss on several objective quality metrics.

The measurement of room acoustics plays a wide role in audio research, from physical acoustics modelling and virtual reality applications to speech enhancement. While vast literature exists on position-dependent room acoustics and coupling of rooms, little has explored the transition from one room to its neighbour. This paper presents the measurement and analysis of a dataset of spatial room impulse responses for the transition between four coupled room pairs. Each transition consists of 101 impulse responses recorded using a fourth-order spherical microphone array in 5 cm intervals, both with and without a continuous line-of-sight between the source and microphone. A numerical analysis of the room transitions is then presented, including direct-to-reverberant ratio and direction of arrival estimations, along with potential applications and uses of the dataset.

This paper presents the enhancement of speech signals in a noisy environment by using a Two-Sensor Fast Normalized Least Mean Square adaptive algorithm combined with the backward blind source separation structure. A comparative study with other competitive algorithms shows the superiority of the proposed algorithm in terms of various objective criteria such as the segmental signal to noise ratio (SegSNR), the cepstral distance (CD), the system mismatch (SM) and the segmental mean square error (SegMSE).

This paper reviews some existing Speech Enhancement techniques and also proposes a new method for enhancing the speech by combining Compressed Sensing and Kalman filter approaches. This approach is based on reconstruction of noisy speech signal using Compressive Sampling Matching Pursuit (CoSaMP) algorithm and further enhanced by Kalman filter. The performance of the proposed method is evaluated and compared with that of the existing techniques in terms of intelligibility and quality measure parameters of speech. The proposed algorithm shows an improved performance compared to Spectral Subtraction, MMSE, Wiener filter, Signal Subspace, Kalman filter in terms of WSS, LLR, SegSNR, SNRloss, PESQ and overall quality.