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 Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

Generating music with emotion similar to that of an input video is a veryrelevant issue nowadays. Video content creators and automatic movie directorsbenefit from maintaining their viewers engaged, which can be facilitated byproducing novel material eliciting stronger emotions in them. Moreover, there'scurrently a demand for more empathetic computers to aid humans in applicationssuch as augmenting the perception ability of visually and/or hearing impairedpeople. Current approaches overlook the video's emotional characteristics inthe music generation step, only consider static images instead of videos, areunable to generate novel music, and require a high level of human effort andskills. In this study, we propose a novel hybrid deep neural network that usesan Adaptive Neuro-Fuzzy Inference System to predict a video's emotion from itsvisual features and a deep Long Short-Term Memory Recurrent Neural Network togenerate its corresponding audio signals with similar emotional inkling. Theformer is able to appropriately model emotions due to its fuzzy properties, andthe latter is able to model data with dynamic time properties well due to theavailability of the previous hidden state information. The novelty of ourproposed method lies in the extraction of visual emotional features in order totransform them into audio signals with corresponding emotional aspects forusers. Quantitative experiments show low mean absolute errors of 0.217 and0.255 in the Lindsey and DEAP datasets respectively, and similar globalfeatures in the spectrograms. This indicates that our model is able toappropriately perform domain transformation between visual and audio features.Based on experimental results, our model can effectively generate audio thatmatches the scene eliciting a similar emotion from the viewer in both datasets,and music generated by our model is also chosen more often.

Emotional Video to Audio Transformation Using Deep Recurrent Neural Networks and a Neuro-Fuzzy System