# Beat this! Accurate beat tracking without DBN postprocessing

arXiv: https://arxiv.org/abs/2407.21658 · HTML: https://mlsanity.com/paper/2407.21658/

## Key facts

- Cited by 27 papers in the map (data through 14 Oct 2026).
- Builds on 14 of its 42 references that are in the map.
- First posted on arXiv 31 Jul 2024.

## Builds on (most cited first, 14 of 14)

- [RoFormer: Enhanced Transformer with Rotary Position Embedding](https://mlsanity.com/paper/2104.09864/) (2021)
- [FlashAttention: Fast and Memory-Efficient Exact Attention with IO-Awareness](https://mlsanity.com/paper/2205.14135/) (2022)
- [V-Net: Fully Convolutional Neural Networks for Volumetric Medical Image Segmentation](https://mlsanity.com/paper/1606.04797/) (2016)
- [SpecAugment: A Simple Data Augmentation Method for Automatic Speech Recognition](https://mlsanity.com/paper/1904.08779/) (2019)
- [A Novel Focal Tversky loss function with improved Attention U-Net for lesion segmentation](https://mlsanity.com/paper/1810.07842/) (2018)
- [Quantizable Transformers: Removing Outliers by Helping Attention Heads Do Nothing](https://mlsanity.com/paper/2306.12929/) (2023)
- [Music Source Separation with Band-Split RoPE Transformer](https://mlsanity.com/paper/2309.02612/) (2023)
- [Learning to Groove with Inverse Sequence Transformations](https://mlsanity.com/paper/1905.06118/) (2019)
- [All-In-One Metrical And Functional Structure Analysis With Neighborhood Attentions on Demixed Audio](https://mlsanity.com/paper/2307.16425/) (2023)
- [Modeling Beats and Downbeats with a Time-Frequency Transformer](https://mlsanity.com/paper/2205.14701/) (2022)
- [Beat Transformer: Demixed Beat and Downbeat Tracking with Dilated Self-Attention](https://mlsanity.com/paper/2209.07140/) (2022)
- [Adapting Meter Tracking Models to Latin American Music](https://mlsanity.com/paper/2304.07186/) (2023)
- [BEAST: Online Joint Beat and Downbeat Tracking Based on Streaming Transformer](https://mlsanity.com/paper/2312.17156/) (2023)
- [Local Periodicity-Based Beat Tracking for Expressive Classical Piano Music](https://mlsanity.com/paper/2308.10355/) (2023)

## Built on by (most cited first, 27 of 27)

- [ACE-Step: A Step Towards Music Generation Foundation Model](https://mlsanity.com/paper/2506.00045/) (2025)
- [MMMG: a Comprehensive and Reliable Benchmark for Multitask Multimodal Generation](https://mlsanity.com/paper/2505.17613/) (2025)
- [UnityShots: Memory-Driven Multi-Shot Audio-Video Generation with Boundary-Aware Gating](https://mlsanity.com/paper/2606.21661/) (2026)
- [Refining music sample identification with a self-supervised graph neural network](https://mlsanity.com/paper/2506.14684/) (2025)
- [DARC: Drum accompaniment generation with fine-grained rhythm control](https://mlsanity.com/paper/2601.02357/) (2026)
- [Towards Real-Time Human-AI Musical Co-Performance: Accompaniment Generation with Latent Diffusion Models and MAX/MSP](https://mlsanity.com/paper/2604.07612/) (2026)
- [LiveBand: Live Accompaniment Generation in the Audio Domain](https://mlsanity.com/paper/2606.03803/) (2026)
- [Beat and Downbeat Tracking in Performance MIDI Using an End-to-End Transformer Architecture](https://mlsanity.com/paper/2507.00466/) (2025)
- [Music Boomerang: Reusing Diffusion Models for Data Augmentation and Audio Manipulation](https://mlsanity.com/paper/2507.04864/) (2025)
- [Segment Transformer: AI-Generated Music Detection via Music Structural Analysis](https://mlsanity.com/paper/2509.08283/) (2025)
- [Fusion Segment Transformer: Bi-Directional Attention Guided Fusion Network for AI-Generated Music Detection](https://mlsanity.com/paper/2601.13647/) (2026)
- [PHALAR: Phasors for Learned Musical Audio Representations](https://mlsanity.com/paper/2605.03929/) (2026)
- [PerceiverS: A Multi-Scale Perceiver with Effective Segmentation for Long-Term Expressive Symbolic Music Generation](https://mlsanity.com/paper/2411.08307/) (2024)
- [LoopGen: Training-Free Loopable Music Generation](https://mlsanity.com/paper/2504.04466/) (2025)
- [High-Resolution Sustain Pedal Depth Estimation from Piano Audio Across Room Acoustics](https://mlsanity.com/paper/2507.04230/) (2025)
- [Exploring System Adaptations For Minimum Latency Real-Time Piano Transcription](https://mlsanity.com/paper/2509.07586/) (2025)
- [Transcribing Rhythmic Patterns of the Guitar Track in Polyphonic Music](https://mlsanity.com/paper/2510.05756/) (2025)
- [AlignBeat: A Latent Variable Model for Multi-Class Beat Tracking from Partially Labeled Data](https://mlsanity.com/paper/2510.14391/) (2025)
- [Joint Estimation of Piano Dynamics and Metrical Structure with a Multi-task Multi-Scale Network](https://mlsanity.com/paper/2510.18190/) (2025)
- [Unsupervised Evaluation of Deep Audio Embeddings for Music Structure Analysis](https://mlsanity.com/paper/2603.27218/) (2026)
- [Rubato: Transcribing Piano Music with Timestamps](https://mlsanity.com/paper/2605.24291/) (2026)
- [LLM-Powered Interactive Robotic Action Synthesis from Multimodal Speech, Gestures, and Music](https://mlsanity.com/paper/2606.31158/) (2026)
- [Masked diffusion enables coherent beat tracking](https://mlsanity.com/paper/2608.04624/) (2026)
- [JazzSAMBA: A Synchronous and Asynchronous Multi-take Band Audio Dataset of Jazz Standards for Live Music Models](https://mlsanity.com/paper/2609.34931/) (2026)
- [LatticeSMC: Where to Spend Inference-Time Compute in Chunked Sequence Generators](https://mlsanity.com/paper/2610.02774/) (2026)
- [Explore This! Beat and Downbeat Tracking From a Learned Tatum Grid](https://mlsanity.com/paper/2610.14817/) (2026)
- [JSIR: An Audio-Aligned, Multi-Task Dataset of Jazz Standard Recordings](https://mlsanity.com/paper/2610.15356/) (2026)

## Abstract (arXiv)

We propose a system for tracking beats and downbeats with two objectives: generality across a diverse music range, and high accuracy. We achieve generality by training on multiple datasets -- including solo instrument recordings, pieces with time signature changes, and classical music with high tempo variations -- and by removing the commonly used Dynamic Bayesian Network (DBN) postprocessing, which introduces constraints on the meter and tempo. For high accuracy, among other improvements, we develop a loss function tolerant to small time shifts of annotations, and an architecture alternating convolutions with transformers either over frequency or time. Our system surpasses the current state of the art in F1 score despite using no DBN. However, it can still fail, especially for difficult and underrepresented genres, and performs worse on continuity metrics, so we publish our model, code, and preprocessed datasets, and invite others to beat this.