Cochleagram-based audio pattern separation using two-dimensional non-negative matrix factorization with automatic sparsity adaptation

Classification of Adventitious Sounds Combining Cochleogram and Vision Transformers

Early identification of respiratory irregularities is critical for improving lung health and reducing global mortality rates. The analysis of respiratory sounds plays a significant role in characterizing the respiratory system's condition and identifying abnormalities. The main contribution of this study is to investigate the performance when the input data, represented by cochleogram, is used to feed the Vision Transformer (ViT) architecture, since this input-classifier combination is the first time it has been applied to adventitious sound classification to our knowledge. Although ViT has shown promising results in audio classification tasks by applying self-attention to spectrogram patches, we extend this approach by applying the cochleogram, which captures specific spectro-temporal features of adventitious sounds. The proposed methodology is evaluated on the ICBHI dataset. We compare the classification performance of ViT with other state-of-the-art CNN approaches using spectrogram, Mel frequency cepstral coefficients, constant-Q transform, and cochleogram as input data. Our results confirm the superior classification performance combining cochleogram and ViT, highlighting the potential of ViT for reliable respiratory sound classification. This study contributes to the ongoing efforts in developing automatic intelligent techniques with the aim to significantly augment the speed and effectiveness of respiratory disease detection, thereby addressing a critical need in the medical field.

Underdetermined reverberant acoustic source separation using weighted full-rank nonnegative tensor models

In this paper, a fusion of K models of full-rank weighted nonnegative tensor factor two-dimensional deconvolution (K-wNTF2D) is proposed to separate the acoustic sources that have been mixed in an underdetermined reverberant environment. The model is adapted in an unsupervised manner under the hybrid framework of the generalized expectation maximization and multiplicative update algorithms. The derivation of the algorithm and the development of proposed full-rank K-wNTF2D will be shown. The algorithm also encodes a set of variable sparsity parameters derived from Gibbs distribution into the K-wNTF2D model. This optimizes each sub-model in K-wNTF2D with the required sparsity to model the time-varying variances of the sources in the spectrogram. In addition, an initialization method is proposed to initialize the parameters in the K-wNTF2D. Experimental results on the underdetermined reverberant mixing environment have shown that the proposed algorithm is effective at separating the mixture with an average signal-to-distortion ratio of 3 dB.

Single-channel blind separation using L₁-sparse complex non-negative matrix factorization for acoustic signals

An innovative method of single-channel blind source separation is proposed. The proposed method is a complex-valued non-negative matrix factorization with probabilistically optimal L1-norm sparsity. This preserves the phase information of the source signals and enforces the inherent structures of the temporal codes to be optimally sparse, thus resulting in more meaningful parts factorization. An efficient algorithm with closed-form expression to compute the parameters of the model including the sparsity has been developed. Real-time acoustic mixtures recorded from a single-channel are used to verify the effectiveness of the proposed method.