• Corpus ID: 8597512

A Multi-model Approach to Beat Tracking Considering Heterogeneous Music Styles

  title={A Multi-model Approach to Beat Tracking Considering Heterogeneous Music Styles},
  author={Sebastian B{\"o}ck and Florian Krebs and Gerhard Widmer},
In this paper we present a new beat tracking algorithm which extends an existing state-of-the-art system with a multi-model approach to represent different music styles. The system uses multiple recurrent neural networks, which are specialised on certain musical styles, to estimate possible beat positions. It chooses the model with the most appropriate beat activation function for the input signal and jointly models the tempo and phase of the beats from this activation function with a dynamic… 

Figures and Tables from this paper

Style-Specific Beat Tracking with Deep Neural Networks
The proposed beat tracking system is based on temporal convolutional networks which capture the sequential structure of audio input and is evaluated on four datasets of various musical genres and styles and achieves state-of-the-art performance.
A Music Structure Informed Downbeat Tracking System Using Skip-chain Conditional Random Fields and Deep Learning
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.
Joint Beat and Downbeat Tracking with Recurrent Neural Networks
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.
Downbeat Tracking Using Beat Synchronous Features with Recurrent Neural Networks
A system that extracts the downbeat times from a beat-synchronous audio feature stream of a music piece and shows on seven commonly used datasets of Western music that the system is able to achieve state-of-the-art results.
Multi-Task Learning of Tempo and Beat: Learning One to Improve the Other
A multi-task learning approach for simultaneous tempo estimation and beat tracking of musical audio that is not only able to exploit the mutual information of both tasks by learning a common, shared representation, but can also improve one by learning only from the other.
Predictive Real-Time Beat Tracking from Music for Embedded Application
A real-time beat tracking algorithm, fast enough to be implemented on an embedded system, that can satisfactorily estimate beat positions from a music signal in real- time with an average continuity score of 0.67.
A Novel 1D State Space for Efficient Music Rhythmic Analysis
This paper proposes a new state space approach for music time structure analysis that collapses the commonly used 2D state spaces into 1D through a jump-back reward strategy, and reduces the state space size drastically.
Beat Tracking with a Cepstroid Invariant Neural Network
A novel rhythm tracking architecture that learns how to track tempo and beats through layered learning, and uses a neural network that is invariant with regards to the cepstroid length.
Drum-Aware Ensemble Architecture for Improved Joint Musical Beat and Downbeat Tracking
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.
A generalized Bayesian model for tracking long metrical cycles in acoustic music signals
A novel generalization to an existing Bayesian model for meter tracking that overcomes this limitation and opens the way for computational analysis of performances with long metrical cycles, and has important applications in music studies as well as in commercial applications that involve such musics.


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.
Context-Dependent Beat Tracking of Musical Audio
A simple and efficient method for beat tracking of musical audio using a two state model that replicates the human ability of tapping in time to music at significantly reduced computational cost.
Evaluation Methods for Musical Audio Beat Tracking Algorithms
This paper presents a review of existing evaluation models and a new method based on a novel visualisation for beat tracking performance, the beat error histogram, and makes a set of recommendations for comparative beat tracking experiments.
Multi-Feature Beat Tracking
Through extended evaluation on a large annotated database, it is shown that the multi-feature beat tracker can outperform the state of the art, and thereby demonstrate that there is sufficient diversity in input features for beat tracking, without the need for multiple tracking models.
Selective Sampling for Beat Tracking Evaluation
In this paper, we propose a method that can identify challenging music samples for beat tracking without ground truth. Our method, motivated by the machine learning method “selective sampling,” is
Reliability-Informed Beat Tracking of Musical Signals
A new probabilistic framework for beat tracking of musical audio and shows how reliability information can be successfully used to increase the mean performance of the proposed algorithm and discusses how far automatic beat tracking is from human tapping.
Beat Tracking using an Autocorrelation Phase Matrix
  • D. Eck
  • Computer Science
    2007 IEEE International Conference on Acoustics, Speech and Signal Processing - ICASSP '07
  • 2007
A novel method for estimating beat from digital audio by computing individual APMs over short overlapping segments of an onset trace derived from the audio using an adaptation of Viterbi decoding to search the APMs for metrical combinations of points that change smoothly over time in the lag/phase plane.
Rhythmic Pattern Modeling for Beat and Downbeat Tracking in Musical Audio
The results showed that explicitly modeling rhythmic patterns of dance styles drastically reduces octave errors (detection of half or double tempo) and substantially improves downbeat tracking.
Particle Filtering Applied to Musical Tempo Tracking
This paper explores the use of particle filters for beat tracking in musical audio examples with two alternative algorithms, one which performs Rao-Blackwellisation to produce an almost deterministic formulation while the second is a formulation which models tempo as a Brownian motion process.
Bayesian Modelling of Temporal Structure in Musical Audio
This paper presents a probabilistic model of temporal structure in music which allows joint inference of tempo, meter and rhythmic pattern. The framework of the model naturally quantifies these three