#INSTALLING THIS VERSION

!pip install -q cython
!pip install -q numba
!pip install -q librosa
!pip install -q mido
!pip install -q pytest
!pip install -q scipy
!pip install -q numpy
!pip install -q torch
!apt-get install portaudio19-dev
!pip install -q pyaudio
!pip install -q pydub
!pip install --upgrade --no-deps --force-reinstall --quiet 'git+https://github.com/CPJKU/madmom.git'
!pip install --upgrade --no-deps --force-reinstall --quiet 'git+https://github.com/davies-w/BeatNet.git'

from BeatNet.BeatNet import BeatNet

#wf, sr = mp3_to_norm_wav("born.mp3") whatever you do to load your mp3 into a wav

estimator = BeatNet(2, mode='offline', inference_model='DBN', plot=[], thread=False)
x=estimator.process(wf)
print(x)

Announcement

Streaming and realtime capabilities are recently added to the model. In streaming usage cases, make sure to feed the system with as loud input as possible to laverage the maximum streaming performance, given all models are trained on the datasets containing mastered songs.

BeatNet

The BeatNet is a package for AI-based music online and offline rhythmic information analysis including music Beat, downbeat, tempo and meter tracking.

This repository contains the user package and the source code of the Monte Carlo particle flitering inference model of the "BeatNet" music online joint beat/downbeat/tempo/meter tracking system. The arxiv version of the original ISMIR-2021 paper:

In addition to the proposed online inference, we added madmom's DBN beat/downbeat inference model for the offline usages. Note that, the offline model still utilize BeatNet's neural network rather than that of Madmom which leads to better performance and significantly faster results.

Note: All models are trained using pytorch and are included in the models folder. In order to recieve the training script and the datasets data/feature handlers, shoot me an email at mheydari [at] ur.rochester.edu

System Input:

Raw audio waveform object or directory.

• By using the audio directory as the system input, the system automatically resamples the audio file to 22050 Hz. However, in the case of using an audio object as the input, make sure that the audio sample rate is equal to 22050 Hz.

System Output:

A vector including beats and downbeats columns, respectively with the following shape: numpy_array(num_beats, 2).

Input Parameters:

model: An scalar in the range [1,3] to select which pre-trained CRNN models to utilize.

mode: An string to determine the working mode. i.e. 'stream', 'realtime', 'online' and 'offline'.

inference model: A string to choose the inference approach. i.e. 'PF' standing for Particle Filtering for causal inferences and 'DBN' standing for Dynamic Bayesian Network for non-causal usages.

plot: A list of strings to plot. It can include 'activations', 'beat_particles' and 'downbeat_particles' Note that to speed up plotting the figures, rather than new plots per frame, the previous plots get updated. However, to secure realtime results, it is recommended to not plot or have as less number of plots as possible at the time.

thread: To decide whether accomplish the inference at the main thread or another thread.

device: Type of device being used. Cuda or cpu (by default).

Installation command:

Approach #1: Installing binaries from the pypi website:

pip install BeatNet

Approach #2: Installing directly from the Git repository:

pip install git+https://github.com/mjhydri/BeatNet

• Note that by using either of the approaches all dependencies and required packages get installed automatically except pyaudio and cython. You mau need to install cython in advance. Also, pyaudio is a python binding for Portaudio to handle audio streaming. If Pyaudio is not installed in your machine, depending on your machine type either install it thorugh pip (Mac OS and Linux) or download an appropriate version for your machine (Windows) from here. Then, navigate to the file location through commandline and use the following command to install the wheel file locally:

pip install <Pyaduio_file_name.whl>     

Usage example 1 (Streaming mode):

from BeatNet.BeatNet import BeatNet

estimator = BeatNet(1, mode='stream', inference_model='PF', plot=[], thread=False)

Output = estimator.process()

Usage example 2 (Realtime mode):

from BeatNet.BeatNet import BeatNet

estimator = BeatNet(1, mode='realtime', inference_model='PF', plot=['beat_particles'], thread=False)

Output = estimator.process("audio file directory")

Usage example 3 (Online mode):

from BeatNet.BeatNet import BeatNet

estimator = BeatNet(1, mode='online', inference_model='PF', plot=['activations'], thread=False)

Output = estimator.process("audio file directory")

Usage example 4 (Offline mode):

from BeatNet.BeatNet import BeatNet

estimator = BeatNet(1, mode='offline', inference_model='DBN', plot=[], thread=False)

Output = estimator.process("audio file directory")

Video Tutorial:

1: In this tutorial, we explain the BeatNet mechanism.

---

Video Demos:

In order to demonstrate the performance of the system for different beat/donbeat tracking difficulties, here are three video demo examples :

1: Song Difficulty: Easy

2: Song difficulty: Medium

3: Song difficulty: Veteran

Acknowledgements:

For the input feature extraction and the raw state space generation, Librosa and Madmom libraries are ustilzed respectively. Many thanks for their great jobs. This work has been partially supported by the National Science Foundation grants 1846184 and DGE-1922591.

arXiv 2108.03576

Cite:

@inproceedings{heydari2021beatnet,
  title={BeatNet: CRNN and Particle Filtering for Online Joint Beat Downbeat and Meter Tracking},
  author={Heydari, Mojtaba and Cwitkowitz, Frank and Duan, Zhiyao},
  journal={22th International Society for Music Information Retrieval Conference, ISMIR},
  year={2021}
}

@inproceedings{heydari2021don,
  title={Don’t look back: An online beat tracking method using RNN and enhanced particle filtering},
  author={Heydari, Mojtaba and Duan, Zhiyao},
  booktitle={ICASSP 2021-2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)},
  pages={236--240},
  year={2021},
  organization={IEEE}
}