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

We propose MoodNet - A Deep Convolutional Neural Network based architectureto effectively predict the emotion associated with a piece of music given itsaudio and lyrical content.We evaluate different architectures consisting ofvarying number of two-dimensional convolutional and subsampling layers,followedby dense layers.We use Mel-Spectrograms to represent the audio content and wordembeddings-specifically 100 dimensional word vectors, to represent the textualcontent represented by the lyrics.We feed input data from both modalities toour MoodNet architecture.The output from both the modalities are then fused asa fully connected layer and softmax classfier is used to predict the categoryof emotion.Using F1-score as our metric,our results show excellent performanceof MoodNet over the two datasets we experimented on-The MIREX Multimodaldataset and the Million Song Dataset.Our experiments reflect the hypothesisthat more complex models perform better with more training data.We also observethat lyrics outperform audio as a better expressed modality and conclude thatcombining and using features from multiple modalities for prediction tasksresult in superior performance in comparison to using a single modality asinput.

A Multimodal Approach towards Emotion Recognition of Music using Audio and Lyrical Content