PiJAMA: Piano Jazz with Automatic MIDI Annotations

Drew Edwards; Simon Dixon; Emmanouil Benetos

doi:10.5334/tismir.162

Abstract

Recent advances in automatic piano transcription have enabled large scale analysis of piano music in the symbolic domain. However, the research has largely focused on classical piano music. We present PiJAMA (Piano Jazz with Automatic MIDI Annotations): a dataset of over 200 hours of solo jazz piano performances with automatically transcribed MIDI. In total there are 2,777 unique performances by 120 different pianists across 244 recorded albums. The dataset contains a mixture of studio recordings and live performances. We use automatic audio tagging to identify applause, spoken introductions, and other non-piano audio to facilitate downstream music information retrieval tasks. We explore descriptive statistics of the MIDI data, including pitch histograms and chromaticism. We then demonstrate two experimental benchmarks on the data: performer identification and generative modeling. The dataset, including a link to the associated source code is available at https://almostimplemented.github.io/PiJAMA/.

References

Balke, S., Reck, J., Weis, C., Abeser, J., and Muller, M. (2022). JSD: A dataset for structure analysis in jazz music. Transactions of the International Society for Music Information Retrieval, 5(1):156–172. DOI: 10.5334/tismir.131
Open DOI Search in Google Scholar Back to article
Bayley, L. R. (2023). Granz’ Art Tatum recordings: A piano method for jazz. https://artmusiclounge.wordpress.com/2023/01/26/granz-art-tatum-recordings-a-piano-method-for-jazz/.
Search in Google Scholar Back to article
Elsdon, P. S. (2001). Keith Jarrett’s solo concerts and the aesthetics of free improvisation 1960–1973. PhD thesis, University of Southampton.
Search in Google Scholar Back to article
Emiya, V., Bertin, N., David, B., and Badeau, R. (2010). MAPS – A piano database for multipitch estimation and automatic transcription of music. Research report inria-00544155, Telecom ParisTech.
Search in Google Scholar Back to article
Eremenko, V., Demirel, E., Bozkurt, B., and Serra, X. (2018). Audio-aligned jazz harmony dataset for automatic chord transcription and corpus-based research. In Proceedings of the 19th International Society for Music Information Retrieval Conference.
Search in Google Scholar Back to article
Flexer, A. and Schnitzer, D. (2010). Effects of album and artist filters in audio similarity computed for very large music databases. Computer Music Journal, 34(3):20–28. DOI: 10.1162/COMJ_a_00004
Open DOI Search in Google Scholar Back to article
Forte, A. (1962). Tonal Harmony in Concept and Practice. Holt, Rinehart and Winston.
Search in Google Scholar Back to article
Gardner, J. P., Simon, I., Manilow, E., Hawthorne, C., and Engel, J. (2022). MT3: Multi-task multitrack music transcription. In International Conference on Learning Representations.
Search in Google Scholar Back to article
Gong, Y., Chung, Y.-A., and Glass, J. (2021). AST: Audio Spectrogram Transformer. In Proceedings of Interspeech 2021, pages 571–575. DOI: 10.21437/Interspeech.2021–;698
Open DOI Search in Google Scholar Back to article
Goto, M., Hashiguchi, H., Nishimura, T., and Oka, R. (2002). RWC Music Database: Popular, Classical and Jazz Music Databases. In Proceedings of the 3rd International Conference on Music Information Retrieval, Paris, France. ISMIR.
Search in Google Scholar Back to article
Hawthorne, C., Elsen, E., Song, J., Roberts, A., Simon, I., Raffel, C., Engel, J., Oore, S., and Eck, D. (2018). Onsets and frames: Dual-objective piano transcription. In Proceedings of the 19th International Society for Music Information Retrieval Conference.
Search in Google Scholar Back to article
Hawthorne, C., Simon, I., Swavely, R., Manilow, E., and Engel, J. (2021). Sequence-to-sequence piano transcription with transformers. In Proceedings of the 22nd International Society for Music Information Retrieval Conference.
Search in Google Scholar Back to article
Hawthorne, C., Stasyuk, A., Roberts, A., Simon, I., Huang, C.-Z. A., Dieleman, S., Elsen, E., Engel, J., and Eck, D. (2019). Enabling factorized piano music modeling and generation with the MAESTRO dataset. In International Conference on Learning Representations.
Search in Google Scholar Back to article
Höger, F., Frieler, K., Pfleiderer, M., and Dixon, S. (2019). Dig that lick: Exploring melodic patterns in jazz improvisation. In 20th International Society for Music Information Retrieval Conference: Late Breaking Demo.
Search in Google Scholar Back to article
Huang, C.-Z. A., Vaswani, A., Uszkoreit, J., Simon, I., Hawthorne, C., Shazeer, N., Dai, A. M., Hoffman, M. D., Dinculescu, M., and Eck, D. (2019). Music transformer. In International Conference on Learning Representations.
Search in Google Scholar Back to article
Kelz, R., Dorfer, M., Korzeniowski, F., Bock, S., Arzt, A., and Widmer, G. (2016). On the potential of simple framewise approaches to piano transcription. In Proceedings of the 17th International Society for Music Information Retrieval Conference, pages 475–481.
Search in Google Scholar Back to article
Kong, Q., Li, B., Chen, J., and Wang, Y. (2022). GiantMIDI-piano: A large-scale MIDI dataset for classical piano music. Transactions of the International Society for Music Information Retrieval, 5(1):87–98. DOI: 10.5334/tismir.80
Open DOI Search in Google Scholar Back to article
Kong, Q., Li, B., Song, X., Wan, Y., and Wang, Y. (2021). High-resolution piano transcription with pedals by regressing onset and offset times. IEEE/ACM Transactions on Audio, Speech and Language Processing, 29:3707–3717. DOI: 10.1109/TASLP.2021.3121991
Open DOI Search in Google Scholar Back to article
Levine, M. (1989). The Jazz Piano Book. Sher Music Co.
Search in Google Scholar Back to article
Pfleiderer, M., Frieler, K., Abeser, J., Zaddach, W.-G., and Burkhart, B., editors (2017). Inside the Jazzomat – New Perspectives for Jazz Research. Schott Campus.
Search in Google Scholar Back to article
Redmon, J., Divvala, S., Girshick, R., and Farhadi, A. (2016). You only look once: Unified, real-time object detection. CoRR. http://arxiv.org/abs/1506.02640. DOI: 10.1109/CVPR.2016.91
Open DOI Search in Google Scholar Back to article
Rodríguez-Algarra, F., Sturm, B. L., and Dixon, S. (2019). Characterising confounding effects in music classification experiments through interventions. Transactions of the International Society for Music Information Retrieval, 2(1):52–66. DOI: 10.5334/tismir.24
Open DOI Search in Google Scholar Back to article
Sigtia, S., Benetos, E., and Dixon, S. (2016). An end-to-end neural network for polyphonic piano music transcription. IEEE/ACM Transactions on Audio, Speech and Language Processing, 24(5):927–939. DOI: 10.1109/TASLP.2016.2533858
Open DOI Search in Google Scholar Back to article
Simon, I., Huang, C.-Z. A., Engel, J., Hawthorne, C., and Dinculescu, M. (2019). Generating piano music with transformer. https://magenta.tensorflow.org/piano-transformer.
Search in Google Scholar Back to article
Siskind, J. (2020). Playing Solo Jazz Piano: A New Approach for Creative Pianists. Jeremy Siskind Music Publishing.
Search in Google Scholar Back to article
Swartz, A. (2002). MusicBrainz: A semantic web service. IEEE Intelligent Systems, 17(1):76–77. DOI: 10.1109/5254.988466
Open DOI Search in Google Scholar Back to article
Taylor, B. (1975). The History and Development of Jazz Piano: A New Perspective for Educators. University of Massachusetts Amherst.
Search in Google Scholar Back to article
Zhang, H., Tang, J., Rafee, S., Dixon, S., and Fazekas, G. (2022). ATEPP: A dataset of automatically transcribed expressive piano performance. In Proceedings of the 23rd International Society for Music Information Retrieval Conference, pages 446–453.
Search in Google Scholar Back to article

PiJAMA: Piano Jazz with Automatic MIDI Annotations

Abstract

Paradigm

My account