mlsanityData to 7 Oct 2026

Addressing Emotion Bias in Music Emotion Recognition and Generation with Frechet Audio Distance

arXiv 2409.15545 ↗First posted 23 Sep 2024eess.AS cs.CL cs.MMcited by 0

Not on the map. Why?

Abstract (arXiv)

The complex nature of musical emotion introduces inherent bias in both recognition and generation, particularly when relying on a single audio encoder, emotion classifier, or evaluation metric. In this work, we conduct a study on Music Emotion Recognition (MER) and Emotional Music Generation (EMG), employing diverse audio encoders alongside Frechet Audio Distance (FAD), a reference-free evaluation metric. Our study begins with a benchmark evaluation of MER, highlighting the limitations of using a single audio encoder and the disparities observed across different measurements. We then propose assessing MER performance using FAD derived from multiple encoders to provide a more objective measure of musical emotion. Furthermore, we introduce an enhanced EMG approach designed to improve both the variability and prominence of generated musical emotion, thereby enhancing its realism. Additionally, we investigate the differences in realism between the emotions conveyed in real and synthetic music, comparing our EMG model against two baseline models. Experimental results underscore the issue of emotion bias in both MER and EMG and demonstrate the potential of using FAD and diverse audio encoders to evaluate musical emotion more objectively and effectively.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 17 of its 36 references that are in the map. First posted on arXiv 23 Sep 2024.

Builds on

17 of 36 references.

References · 17

  1. 2022Large-scale Contrastive Language-Audio Pretraining with Feature Fusion and Keyword-to-Caption Augmentationcited by 707
  2. 2016CNN Architectures for Large-Scale Audio Classificationcited by 701
  3. 2022High Fidelity Neural Audio Compressioncited by 673
  4. 2023High-Fidelity Audio Compression with Improved RVQGANcited by 423
  5. 2018Music Transformercited by 207
  6. 2023MERT: Acoustic Music Understanding Model with Large-Scale Self-supervised Trainingcited by 175
  7. 2017MuseGAN: Multi-track Sequential Generative Adversarial Networks for Symbolic Music Generation and Accompanimentcited by 151
  8. 2023Adapting Frechet Audio Distance for Generative Music Evaluationcited by 92
  9. 2021Codified audio language modeling learns useful representations for music information retrievalcited by 61
  10. 2023Natural Language Supervision for General-Purpose Audio Representationscited by 60
  11. 2021EMOPIA: A Multi-Modal Pop Piano Dataset For Emotion Recognition and Emotion-based Music Generationcited by 53
  12. 2021CDPAM: Contrastive learning for perceptual audio similaritycited by 42
5 more
  1. 2022Exploration of A Self-Supervised Speech Model: A Study on Emotional Corporacited by 31
  2. 2022Symbolic music generation conditioned on continuous-valued emotionscited by 12
  3. 2022Controlling Perceived Emotion in Symbolic Music Generation with Monte Carlo Tree Searchcited by 11
  4. 2024Layer-Wise Analysis of Self-Supervised Acoustic Word Embeddings: A Study on Speech Emotion Recognitioncited by 8
  5. 2023EmoGen: Eliminating Subjective Bias in Emotional Music Generationcited by 4

Built on by

Not cited yet.