mlsanityData to 7 Oct 2026

MuSLCAT: Multi-Scale Multi-Level Convolutional Attention Transformer for Discriminative Music Modeling on Raw Waveforms

arXiv 2104.02309 ↗First posted 6 Apr 2021cs.SD cs.LG eess.AScited by 0

Not on the map. Why?

Abstract (arXiv)

In this work, we aim to improve the expressive capacity of waveform-based discriminative music networks by modeling both sequential (temporal) and hierarchical information in an efficient end-to-end architecture. We present MuSLCAT, or Multi-scale and Multi-level Convolutional Attention Transformer, a novel architecture for learning robust representations of complex music tags directly from raw waveform recordings. We also introduce a lightweight variant of MuSLCAT called MuSLCAN, short for Multi-scale and Multi-level Convolutional Attention Network. Both MuSLCAT and MuSLCAN model features from multiple scales and levels by integrating a frontend-backend architecture. The frontend targets different frequency ranges while modeling long-range dependencies and multi-level interactions by using two convolutional attention networks with attention-augmented convolution (AAC) blocks. The backend dynamically recalibrates multi-scale and level features extracted from the frontend by incorporating self-attention. The difference between MuSLCAT and MuSLCAN is their backend components. MuSLCAT's backend is a modified version of BERT. While MuSLCAN's is a simple AAC block. We validate the proposed MuSLCAT and MuSLCAN architectures by comparing them to state-of-the-art networks on four benchmark datasets for music tagging and genre recognition. Our experiments show that MuSLCAT and MuSLCAN consistently yield competitive results when compared to state-of-the-art waveform-based models yet require considerably fewer parameters.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 30 of its 54 references that are in the map. First posted on arXiv 6 Apr 2021.

Builds on

30 of 54 references.

References · 30

  1. 2017Attention Is All You Needcited by 59,932
  2. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  3. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,204
  4. 2019PyTorch: An Imperative Style, High-Performance Deep Learning Librarycited by 20,160
  5. 2014Very Deep Convolutional Networks for Large-Scale Image Recognitioncited by 15,267
  6. 2015Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shiftcited by 6,979
  7. 2016Layer Normalizationcited by 5,579
  8. 2017Squeeze-and-Excitation Networkscited by 4,763
  9. 2014Neural Machine Translation by Jointly Learning to Align and Translatecited by 4,530
  10. 2018Self-Attention with Relative Position Representationscited by 1,112
  11. 2019Attention Augmented Convolutional Networkscited by 363
  12. 2018Music Transformercited by 207
18 more
  1. 2016FMA: A Dataset For Music Analysiscited by 205
  2. 2016Long Short-Term Memory-Networks for Machine Readingcited by 161
  3. 2018Gather-Excite: Exploiting Feature Context in Convolutional Neural Networkscited by 138
  4. 2016Convolutional Recurrent Neural Networks for Music Classificationcited by 49
  5. 2016Automatic tagging using deep convolutional neural networkscited by 39
  6. 2020Evaluation of CNN-based Automatic Music Tagging Modelscited by 39
  7. 2019Encoding Musical Style with Transformer Autoencoderscited by 35
  8. 2019Toward Interpretable Music Tagging with Self-Attentioncited by 29
  9. 2017End-to-end learning for music audio tagging at scalecited by 25
  10. 2019A Bi-directional Transformer for Musical Chord Recognitioncited by 19
  11. 2020Pop Music Transformer: Beat-based Modeling and Generation of Expressive Pop Piano Compositionscited by 16
  12. 2017Sample-level CNN Architectures for Music Auto-tagging Using Raw Waveformscited by 12
  13. 2013The GTZAN dataset: Its contents, its faults, their effects on evaluation, and its future usecited by 11
  14. 2016Learning Multiscale Features Directly From Waveformscited by 9
  15. 2017Multi-Level and Multi-Scale Feature Aggregation Using Pre-trained Convolutional Neural Networks for Music Auto-taggingcited by 8
  16. 2017Multi-label Music Genre Classification from Audio, Text, and Images Using Deep Featurescited by 7
  17. 2020Voice and accompaniment separation in music using self-attention convolutional neural networkcited by 3
  18. 2017Multi-Level and Multi-Scale Feature Aggregation Using Sample-level Deep Convolutional Neural Networks for Music Classificationcited by 1

Built on by

Not cited yet.