MAESTRO

MAESTRO (MIDI and Audio Edited for Synchronous TRacks and Organization) is a dataset composed of about 200 hours of virtuosic piano performances captured with fine alignment (~3 ms) between note labels and audio waveforms. We partnered with organizers of the International Piano-e-Competition for the raw data used in this dataset. During each installment of the competition virtuoso pianists perform on Yamaha Disklaviers which, in addition to being concert-quality acoustic grand pianos, utilize an integrated high-precision MIDI capture and playback system. Recorded MIDI data is of sufficient fidelity to allow the audition stage of the competition to be judged remotely by listening to contestant performances reproduced over the wire on another Disklavier instrument. The dataset contains about 200 hours of paired audio and MIDI recordings from ten years of International Piano-e-Competition. The MIDI data includes key strike velocities and sustain/sostenuto/una corda pedal positions. Audio and MIDI files are aligned with ∼3 ms accuracy and sliced to individual musical pieces, which are annotated with composer, title, and year of performance. Uncompressed audio is of CD quality or higher (44.1–48 kHz 16-bit PCM stereo). A train/validation/test split configuration is also proposed, so that the same composition, even if performed by multiple contestants, does not appear in multiple subsets. Repertoire is mostly classical, including composers from the 17th to early 20th century. For more information about how the dataset was created and several applications of it, please see the paper where it was introduced: Enabling Factorized Piano Music Modeling and Generation with the MAESTRO Dataset. For an example application of the dataset, see our blog post on Wave2Midi2Wave. Additional information is available on the Magenta website: The MAESTRO Dataset If you use the MAESTRO dataset in your work, please cite the paper where it was introduced: <pre>Curtis Hawthorne, Andriy Stasyuk, Adam Roberts, Ian Simon, Cheng-Zhi Anna Huang, Sander Dieleman, Erich Elsen, Jesse Engel, and Douglas Eck. "Enabling Factorized Piano Music Modeling and Generation with the MAESTRO Dataset." In International Conference on Learning Representations, 2019. </pre> You can also use the following BibTeX entry: <pre>@inproceedings{ hawthorne2018enabling, title={Enabling Factorized Piano Music Modeling and Generation with the {MAESTRO} Dataset}, author={Curtis Hawthorne and Andriy Stasyuk and Adam Roberts and Ian Simon and Cheng-Zhi Anna Huang and Sander Dieleman and Erich Elsen and Jesse Engel and Douglas Eck}, booktitle={International Conference on Learning Representations}, year={2019}, url={https://openreview.net/forum?id=r1lYRjC9F7}, } </pre> Please also make sure to specify which version of the dataset you are using. MAESTRO is provided as a zip file containing the MIDI and WAV files as well as metadata in CSV and JSON formats. A MIDI-only archive of the dataset is also available.MAESTRO（全称MIDI and Audio Edited for Synchronous TRacks and Organization，即面向同步音轨与结构化管理的MIDI与音频数据集）是一个包含约200小时大师级钢琴演奏音频的数据集，其音符标注与音频波形间的对齐精度可达约3毫秒。本数据集的原始数据由我们与国际钢琴电子大赛（International Piano-e-Competition）的主办方合作获取。 在该赛事的每一届比赛中，参赛的杰出钢琴家均使用雅马哈Disklavier钢琴进行演奏。该乐器不仅具备音乐会级品质的三角钢琴声学性能，还集成了高精度的MIDI采集与回放系统。录制得到的MIDI数据拥有极高保真度，足以支持大赛的远程评审环节：评审人员可通过另一台Disklavier乐器回放参赛选手的演奏，完成远程评判。 本数据集涵盖了十届国际钢琴电子大赛中录制的约200小时配对音频与MIDI录音。其中MIDI数据包含琴键击键速度、延音踏板、持音踏板及柔音踏板的位置信息。音频与MIDI文件的对齐精度约为3毫秒，且已被切割为单首乐曲，并标注了作曲家、作品标题以及演奏年份。未压缩音频达到CD音质及以上规格（44.1–48 kHz、16位PCM立体声）。 我们还提供了训练集/验证集/测试集的划分方案，确保同一首作品即使由多位选手演奏，也不会同时出现在多个划分子集当中。该数据集的演奏曲目以古典音乐为主，涵盖17世纪至20世纪早期的作曲家作品。 若想了解该数据集的构建方式与具体应用场景，请参阅其首发论文《基于MAESTRO数据集实现分解式钢琴音乐建模与生成》（Enabling Factorized Piano Music Modeling and Generation with the MAESTRO Dataset）。若想查看该数据集的示例应用，请参阅我们发布的《Wave2Midi2Wave》博客文章。更多相关信息可访问Magenta官网的MAESTRO数据集页面。 若您在研究工作中使用MAESTRO数据集，请引用其首发论文： Curtis Hawthorne, Andriy Stasyuk, Adam Roberts, Ian Simon, Cheng-Zhi Anna Huang, Sander Dieleman, Erich Elsen, Jesse Engel, and Douglas Eck. "Enabling Factorized Piano Music Modeling and Generation with the MAESTRO Dataset." In International Conference on Learning Representations, 2019. 您也可以使用以下BibTeX条目： <pre>@inproceedings{ hawthorne2018enabling, title={Enabling Factorized Piano Music Modeling and Generation with the {MAESTRO} Dataset}, author={Curtis Hawthorne and Andriy Stasyuk and Adam Roberts and Ian Simon and Cheng-Zhi Anna Huang and Sander Dieleman and Erich Elsen and Jesse Engel and Douglas Eck}, booktitle={International Conference on Learning Representations}, year={2019}, url={https://openreview.net/forum?id=r1lYRjC9F7}, }</pre> 数据集以zip压缩包形式提供，内含MIDI文件、WAV音频文件以及CSV与JSON格式的元数据。我们还提供了仅包含MIDI数据的数据集归档包。请务必注明您所使用的MAESTRO数据集版本。