English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Tools annual

Global: Zendy Free Plan

Global: Zendy Tools monthly

Global: Zendy Plus monthly

Digital audio signal reconstruction of a lost or corrupt segment using deeplearning algorithms has been explored intensively in recent years.Nevertheless, prior traditional methods with linear interpolation, phase codingand tone insertion techniques are still in vogue. However, we found no researchwork on reconstructing audio signals with the fusion of dithering,steganography, and machine learning regressors. Therefore, this paper proposesthe combination of steganography, halftoning (dithering), and state-of-the-artshallow and deep learning methods. The results (including comparing the SPAIN,Autoregressive, deep learning-based, graph-based, and other methods) areevaluated with three different metrics. The observations from the results showthat the proposed solution is effective and can enhance the reconstruction ofaudio signals performed by the side information (e.g., Latent representation)steganography provides. Moreover, this paper proposes a novel framework forreconstruction from heavily compressed embedded audio data using halftoning(i.e., dithering) and machine learning, which we termed the HCR (halftone-basedcompression and reconstruction). This work may trigger interest in optimisingthis approach and/or transferring it to different domains (i.e., imagereconstruction). Compared to existing methods, we show improvement in theinpainting performance in terms of signal-to-noise ratio (SNR), the objectivedifference grade (ODG) and Hansen's audio quality metric. In particular, ourproposed framework outperformed the learning-based methods (D2WGAN and SG) andthe traditional statistical algorithms (e.g., SPAIN, TDC, WCP).

Active Restoration of Lost Audio Signals Using Machine Learning and Latent Information