• Corpus ID: 15831944

Joint Beat and Downbeat Tracking with Recurrent Neural Networks

@inproceedings{Bck2016JointBA,
  title={Joint Beat and Downbeat Tracking with Recurrent Neural Networks},
  author={Sebastian B{\"o}ck and Florian Krebs and Gerhard Widmer},
  booktitle={ISMIR},
  year={2016}
}
In this paper we present a novel method for jointly extracting beats and downbeats from audio signals. A recurrent neural network operating directly on magnitude spectrograms is used to model the metrical structure of the audio signals at multiple levels and provides an output feature that clearly distinguishes between beats and downbeats. A dynamic Bayesian network is then used to model bars of variable length and align the predicted beat and downbeat positions to the global best solution. We… 
View Paper
86 Citations
Highly Influential Citations
17
Background Citations
33
Methods Citations
47
Results Citations
2

Figures and Tables from this paper

86 Citations

Citation Type

Citation Type

Temporal convolutional networks for musical audio beat tracking
TLDR
Three highly promising attributes of TCNs for music analysis are demonstrated, namely: they achieve state-of-the-art performance on a wide range of existing beat tracking datasets, they are well suited to parallelisation and thus can be trained efficiently even on very large training data, and they require a small number of weights.
Drum-Aware Ensemble Architecture for Improved Joint Musical Beat and Downbeat Tracking
TLDR
Evaluation on four testing sets that feature different levels of presence of drum sounds shows that the new architecture consistently outperforms the widely-adopted baseline architecture that does not employ source separation.
PHASE-AWARE JOINT BEAT AND DOWNBEAT ESTIMATION BASED ON PERIODICITY OF METRICAL STRUCTURE
TLDR
A phase-aware joint beat and downbeat estimation method mainly intended for popular music with a periodic metrical structure and steady tempo that trains a DNN that estimates the beat phase at each frame whose period is equal to the beat interval.
Self-Supervised Beat Tracking in Musical Signals with Polyphonic Contrastive Learning
TLDR
This work presents a new self-supervised learning pretext task for beat tracking and downbeat estimation that is notably one of the first works to use audio source separation as a fundamental component of selfsupervision.
Modeling Beats and Downbeats with a Time-Frequency Transformer
TLDR
This approach can significantly outperform TCN in downbeat tracking while maintaining comparable result in beat tracking, and combines SpecTNT with a state-of-the-art model, Temporal Convolutional Networks (TCN), to further improve the performance.
Beat and Downbeat Tracking of Symbolic Music Data Using Deep Recurrent Neural Networks
  • Yi-Chin Chuang, Li Su
  • Computer Science
    2020 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC)
  • 2020
TLDR
Experimental results show that the BLSTM model trained specifically on symbolic data outperforms the state-of-the-art beat tracking methods utilized on synthesized audio, which indicates the technical challenges in symbolic music beat tracking.
A Music Structure Informed Downbeat Tracking System Using Skip-chain Conditional Random Fields and Deep Learning
TLDR
This work introduces a skip-chain conditional random field language model for downbeat tracking designed to include section information in an unified and flexible framework and shows that incorporating structure information in the language model leads to more consistent and more robust downbeat estimations.
WaveBeat: End-to-end beat and downbeat tracking in the time domain
TLDR
WaveBeat is proposed, an end-to-end approach for joint beat and downbeat tracking operating directly on waveforms that outperforms previous state-of-the-art methods on some datasets, while producing comparable results on others, demonstrating the potential for time domain approaches.
Drum Transcription via Joint Beat and Drum Modeling Using Convolutional Recurrent Neural Networks
TLDR
It is shown that convolutional and recurrentconvolutional neural networks perform better than state-ofthe-art methods and that learning beats jointly with drums can be beneficial for the task of drum detection.
Analysis of Common Design Choices in Deep Learning Systems for Downbeat Tracking
TLDR
A systematic investigation of the impact of largely adopted variants of convolutional-recurrent networks on downbeat tracking, and finds that temporal granularity has a significant impact on performance.
...
...

References

SHOWING 1-10 OF 32 REFERENCES
Downbeat tracking with multiple features and deep neural networks
TLDR
A novel method for the automatic estimation of downbeat positions from music signals that relies on the computation of musically inspired features capturing important aspects of music such as timbre, harmony, rhythmic patterns, or local similarities in both timbre and harmony.
Feature adapted convolutional neural networks for downbeat tracking
TLDR
A novel system for the automatic estimation of downbeat positions from audio music signals is defined and feature adapted convolutional neural networks are used to take advantage of their specificity to learn downbeat likelihood.
ENHANCED BEAT TRACKING WITH CONTEXT-AWARE NEURAL NETWORKS
TLDR
A bidirectional Long Short-Term Memory recurrent neural network is proposed to perform a frame by frame beat classification of the signal to eliminate the erroneously detected - or complement the missing - beats.
A probabilistic approach to simultaneous extraction of beats and downbeats
TLDR
A novel statistical approach to modeling beat sequences based on the application of Hidden Markov Models (HMM) is introduced and the resulting beat labels are obtained by running the Viterbi decoder and subsequent lattice rescoring.
A Multi-model Approach to Beat Tracking Considering Heterogeneous Music Styles
TLDR
A new beat tracking algorithm which extends an existing state-of-the-art system with a multi-model approach to represent different music styles and is able to match even human tapping performance.
Joint Estimation of Chords and Downbeats From an Audio Signal
TLDR
The results show that the downbeat positions of a music piece can be estimated in terms of its harmonic structure and that conversely the chord progression estimation benefits from considering the interaction between the metric and the harmonic structures.
A spectral difference approach to downbeat extraction in musical audio
TLDR
Using musical knowledge that lower frequency bands are perceptually more important, the spectral difference between band-limited beat synchronous analysis frames is found as a robust downbeat indicator.
Inferring Metrical Structure in Music Using Particle Filters
TLDR
For the first time, the proposedPF system allows fast meter inference in a high-dimensional state space, spanned by the three components of tempo, type of rhythm, and position in a metric cycle.
Enhancing downbeat detection when facing different music styles
  • S. Durand, B. David, G. Richard
  • Computer Science
    2014 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)
  • 2014
TLDR
A novel approach for robust downbeat detection using a note accentuation model and a detection of pattern changes are introduced and the time signature is estimated by examining the similarity of frames at the beat level.
Simultaneous Beat and Downbeat-Tracking Using a Probabilistic Framework: Theory and Large-Scale Evaluation
TLDR
A probabilistic framework in which the time of the beats and their associated beat-position-inside-a-bar roles are considered as hidden states and are estimated simultaneously using signal observations, and a “reverse” Viterbi algorithm which decodes hidden states over beat-numbers is proposed.
...
...