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 Tools annual

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 monthly

Global: Zendy Plus monthly

Presents the access of premium content as premium feature

Premium Content

Global: Zendy Plus annual

Global: Zendy Free Plan

Binaural stereo audio is recorded by imitating the way the human ear receivessound, which provides people with an immersive listening experience. Existingapproaches leverage autoencoders and directly exploit visual spatialinformation to synthesize binaural stereo, resulting in a limitedrepresentation of visual guidance. For the first time, we propose a visuallyguided generative adversarial approach for generating binaural stereo audiofrom mono audio. Specifically, we develop a Stereo Audio Generation Model(SAGM), which utilizes shared spatio-temporal visual information to guide thegenerator and the discriminator to work separately. The shared visualinformation is updated alternately in the generative adversarial stage,allowing the generator and discriminator to deliver their respective guidedknowledge while visually sharing. The proposed method learns bidirectionalcomplementary visual information, which facilitates the expression of visualguidance in generation. In addition, spatial perception is a crucial attributeof binaural stereo audio, and thus the evaluation of stereo spatial perceptionis essential. However, previous metrics failed to measure the spatialperception of audio. To this end, a metric to measure the spatial perception ofaudio is proposed for the first time. The proposed metric is capable ofmeasuring the magnitude and direction of spatial perception in the temporaldimension. Further, considering its function, it is feasible to utilize itinstead of demanding user studies to some extent. The proposed method achievesstate-of-the-art performance on 2 datasets and 5 evaluation metrics.Qualitative experiments and user studies demonstrate that the method generatesspace-realistic stereo audio.

Cross-modal Generative Model for Visual-Guided Binaural Stereo Generation