mlsanityData to 14 Oct 2026

PHALAR: Phasors for Learned Musical Audio Representations

arXiv 2605.03929 ↗First posted 5 May 2026cs.SD cs.AI cs.LGcited by 1

Not on the map. Why?

Abstract (arXiv)

Stem retrieval, the task of matching missing stems to a given audio submix, is a key challenge currently limited by models that discard temporal information. We introduce PHALAR, a contrastive framework achieving a relative accuracy increase of up to ≈ 70% over the state-of-the-art while requiring <50% of the parameters and a 7× training speedup. By utilizing a Learned Spectral Pooling layer and a complex-valued head, PHALAR enforces pitch-equivariant and phase-equivariant biases. PHALAR establishes new retrieval state-of-the-art across MoisesDB, Slakh, and ChocoChorales, correlating significantly higher with human coherence judgment than semantic baselines. Finally, zero-shot beat tracking and linear chord probing confirm that PHALAR captures robust musical structures beyond the retrieval task.

Key facts. Cited by 1 paper in the map (data through 14 Oct 2026). Builds on 39 of its 56 references that are in the map. First posted on arXiv 5 May 2026.

Builds on

39 of 56 references.

References · 39

  1. 2017Attention Is All You Needcited by 60,361
  2. 2020An Image is Worth 16x16 Words: Transformers for Image Recognition at Scalecited by 30,186
  3. 2020A Simple Framework for Contrastive Learning of Visual Representationscited by 12,049
  4. 2018Representation Learning with Contrastive Predictive Codingcited by 7,777
  5. 2015Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shiftcited by 7,005
  6. 2016Layer Normalizationcited by 5,669
  7. 2015Rethinking the Inception Architecture for Computer Visioncited by 5,475
  8. 2020wav2vec 2.0: A Framework for Self-Supervised Learning of Speech Representationscited by 3,905
  9. 2021HuBERT: Self-Supervised Speech Representation Learning by Masked Prediction of Hidden Unitscited by 2,342
  10. 2018Spectral Normalization for Generative Adversarial Networkscited by 1,636
  11. 2016Complex Embeddings for Simple Link Predictioncited by 902
  12. 2019RotatE: Knowledge Graph Embedding by Relational Rotation in Complex Spacecited by 898
27 more
  1. 2022Large-scale Contrastive Language-Audio Pretraining with Feature Fusion and Keyword-to-Caption Augmentationcited by 719
  2. 2016CNN Architectures for Large-Scale Audio Classificationcited by 704
  3. 2022High Fidelity Neural Audio Compressioncited by 687
  4. 2023AudioLDM: Text-to-Audio Generation with Latent Diffusion Modelscited by 599
  5. 2023High-Fidelity Audio Compression with Improved RVQGANcited by 431
  6. 2015Unitary Evolution Recurrent Neural Networkscited by 294
  7. 2017Deep Complex Networkscited by 217
  8. 2024Stable Audio Opencited by 197
  9. 2023MERT: Acoustic Music Understanding Model with Large-Scale Self-supervised Trainingcited by 181
  10. 2020Contrastive Learning of General-Purpose Audio Representationscited by 169
  11. 2025Meta Audiobox Aesthetics: Unified Automatic Quality Assessment for Speech, Music, and Soundcited by 137
  12. 2023Adapting Frechet Audio Distance for Generative Music Evaluationcited by 92
  13. 2019Cutting Music Source Separation Some Slakh: A Dataset to Study the Impact of Training Data Quality and Quantitycited by 86
  14. 2021Contrastive Learning of Musical Representationscited by 82
  15. 2015Spectral Representations for Convolutional Neural Networkscited by 81
  16. 2020ViSQOL v3: An Open Source Production Ready Objective Speech and Audio Metriccited by 79
  17. 2019Phase-aware Speech Enhancement with Deep Complex U-Netcited by 73
  18. 2021CDPAM: Contrastive learning for perceptual audio similaritycited by 42
  19. 2024Beat this! Accurate beat tracking without DBN postprocessingcited by 27
  20. 2019A Bi-directional Transformer for Musical Chord Recognitioncited by 19
  21. 2024COCOLA: Coherence-Oriented Contrastive Learning of Musical Audio Representationscited by 14
  22. 2022The Chamber Ensemble Generator: Limitless High-Quality MIR Data via Generative Modelingcited by 10
  23. 2018Quantum-inspired Complex Word Embeddingcited by 6
  24. 2025STAGE: Stemmed Accompaniment Generation through Prefix-Based Conditioningcited by 6
  25. 2021Quantitative approximation results for complex-valued neural networkscited by 5
  26. 2025Accompaniment Prompt Adherence: A Measure for Evaluating Music Accompaniment Systemscited by 2
  27. 2026EuleroDec: A Complex-Valued RVQ-VAE for Efficient and Robust Audio Codingcited by 1

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2026: 1.

1 paper.

  1. 2026Capturing Cardiac Cyclicity through Phase-Equivariant Self-Supervised Learningcited by 0