Music Mood Detection Based On Audio And Lyrics With Deep Neural Net

Abstract

We consider the task of multimodal music mood prediction based on the audio signal and the lyrics of a track. We reproduce the implementation of traditional feature engineering based approaches and propose a new model based on deep learning. We compare the performance of both approaches on a database containing 18,000 tracks with associated valence and arousal values and show that our approach outperforms classical models on the arousal detection task, and that both approaches perform equally on the valence prediction task. We also compare the a posteriori fusion with fusion of modalities optimized simultaneously with each unimodal model, and observe a significant improvement of valence prediction. We release part of our database for comparison purposes.

arXiv commentPublished in ISMIR 2018

References in corpus (2)

• Efficient Estimation of Word Representations in Vector Space
• On the Properties of Neural Machine Translation: Encoder-Decoder Approaches

Cited by in corpus (5)

• Machine learning for music genre: multifaceted review and experimentation with audioset
• Cold Start Similar Artists Ranking with Gravity-Inspired Graph Autoencoders
• Artificial Musical Intelligence: A Survey
• Exploiting Synchronized Lyrics And Vocal Features For Music Emotion Detection
• Love Me, Love Me, Say (and Write!) that You Love Me: Enriching the WASABI Song Corpus with Lyrics Annotations