International Audio Laboratories Erlangen

Ferienakademie 2024, Sarntal (22.09. - 04.10.2024)

Course 8: Learning with Music Signals

Main Tutor/Lecturer: Hans-Ulrich Berendes, Prof. Dr. Meinard Müller

Group: Automatic Music Transcription (AMT)

Automatic Music Transcription (AMT) is considered one of the fundamental research questions in the field of Music Information Retrieval (MIR). Its general objective is to convert music recordings into a symbolic representation containing information about the instrument, onset time, duration, and velocity for each note event. AMT is challenging because many notes may be played simultaneously (polyphony), different instruments may be active at the same time, sound events may have overlapping partials, and acoustic conditions such as reverberation add complexity. In this group, we discuss various challenges and some recent data-driven techniques based on deep learning for AMT.

Literature

  1. Curtis Hawthorne, Erich Elsen, Jialin Song, Adam Roberts, Ian Simon, Colin Raffel, Jesse H. Engel, Sageev Oore, and Douglas Eck
    Onsets and Frames: Dual-Objective Piano Transcription
    In Proceedings of the International Society for Music Information Retrieval Conference, (ISMIR): 50–57, 2018. PDF DOI 
    @inproceedings{HawthorneESRSRE18_OnsetsFrames_ISMIR,
author    = {Curtis Hawthorne and Erich Elsen and Jialin Song and Adam Roberts and Ian Simon and Colin Raffel and Jesse H. Engel and Sageev Oore and Douglas Eck},
title     = {Onsets and Frames: {D}ual-Objective Piano Transcription},
booktitle = {Proceedings of the International Society for Music Information Retrieval Conference, ({ISMIR})},
pages     = {50--57},
address   = {Paris, France},
doi       = {10.5281/zenodo.1492341},
year      = {2018},
url-pdf   = {2018_HawthorneESRSRE_OnsetsFrames_ISMIR.pdf}
}
  2. Emmanouil Benetos, Simon Dixon, Zhiyao Duan, and Sebastian Ewert
    Automatic Music Transcription: An Overview
    IEEE Signal Processing Magazine, 36(1): 20–30, 2019. PDF DOI 
    @article{BenetosDDE19_MusicTranscription_SPM,
author    = {Emmanouil Benetos and Simon Dixon and Zhiyao Duan and Sebastian Ewert},
title     = {Automatic Music Transcription: {A}n Overview},
journal   = {{IEEE} Signal Processing Magazine},
volume    = {36},
number    = {1},
pages     = {20--30},
year      = {2019},
doi       = {10.1109/MSP.2018.2869928},
url-pdf   = {2019_BenetosDDE_MusicTranscription_SPM.pdf}
}
  3. Ben Maman and Amit H. Bermano
    Unaligned Supervision for Automatic Music Transcription in The Wild
    In Proceedings of the International Conference on Machine Learning (ICML): 14918–14934, 2022. PDF 
    @inproceedings{MamanB22_UnalignedAMT_ICML,
title     = {Unaligned Supervision for Automatic Music Transcription in The Wild},
author    = {Ben Maman and Amit H. Bermano},
booktitle = {Proceedings of the International Conference on Machine Learning ({ICML})},
pages     = {14918--14934},
address   = {Baltimore, Maryland, USA},
year      = {2022},
url-pdf   = {2022_MamanB_UnalignedAMT_ICML.pdf}
}
  4. Xavier Riley, Drew Edwards, and Simon Dixon
    High Resolution Guitar Transcription via Domain Adaptation
    arXiv, abs/2402.15258, 2024. PDF DOI 
    @article{Riley2024_GuitarTranscription_arxiv,
title={High Resolution Guitar Transcription via Domain Adaptation},
author={Xavier Riley and Drew Edwards and Simon Dixon},
year={2024},
volume={abs/2402.15258},
journal={arXiv},
doi={10.48550/arXiv.2402.15258},
url-pdf={2024_Riley_GuitarTranscription_arXiv.pdf}
}
  5. Qiuqiang Kong, Bochen Li, Xuchen Song, Yuan Wan, and Yuxuan Wang
    High-resolution Piano Transcription with Pedals by Regressing Onset and Offset Times
    arXiv, abs/2010.01815, 2021. PDF DOI 
    @article{Kong2021_HighResPianoTranscription_arxiv,
title={High-resolution Piano Transcription with Pedals by Regressing Onset and Offset Times},
author={Qiuqiang Kong and Bochen Li and Xuchen Song and Yuan Wan and Yuxuan Wang},
year={2021},
volume={abs/2010.01815},
journal={arXiv},
doi={10.48550/arXiv.2010.01815}
url-pdf={2021_Kong_HighResPianoTranscription_arXiv.pdf}
}

Further Links