Violin MIDI Dataset

Violin MIDI Transcription Dataset from High-Resolution Violin Transcription using Weak Labels

Description

Overview

A descriptive transcription of a violin performance requires detecting not only the notes but also the fine-grained pitch variations, such as vibrato. Most existing deep learning methods for music transcription do not capture these variations and often need frame-level annotations, which are scarce for the violin. To enable the development of transcription methods tailored for the analysis of violin performances, this dataset includes MIDI files aligned to violin performances with 5.8 ms frame resolution and 10-cent frequency resolution, and includes pitch bends that represent fine-grained deviations such as vibrato and intonation choice.

Dataset Creation

The dataset consists of performances of three violin etude books by 22 violinists. The etude books included are:

• Paganini, Op. 1
• Wohlfahrt, Op. 35
• Kayser, Op. 20

The original MIDI files pre-alignment are sourced from IMSLP and MuseScore (published under Creative Commons license). In the dataset, we provide these open-source MIDI files after they are aligned with the performance links from YouTube. Notably, each MIDI file includes pitch bends to offer a more realistic representation of the expressive performances, and to facilitate intonation analysis for pedagogical applications. The filenames are structured to include reconstructable links to the performances:

composer_catalog_number_performer_YouTube_ID-YouTube_start_sec-YouTube_end_sec.mid

Contributions and Findings

We target the task of descriptive violin transcription with pitch bends, and demonstrate that our method (1) outperforms generic systems in the proxy tasks of violin transcription and pitch estimation, and (2) can automatically generate new training labels by aligning its feature representations with unseen scores. Additionally, we share our model along with 34 hours of score-aligned solo violin performance dataset, notably including the 24 Paganini Caprices.

Citation

If you find this dataset useful, please cite the following paper:

Nazif Can Tamer, Yigitcan Özer, Meinard Müller, Xavier Serra, “High-Resolution Violin Transcription using Weak Labels”, in Proc. of the 24th Int. Society for Music Information Retrieval Conf., Milan, Italy, 2023.

,
  author={Tamer, Nazif Can and "Ozer, Yigitcan and M"uller, Meinard and Serra, Xavier},
  booktitle=International Society for Music Information Retrieval Conference (ISMIR),
<cod