Weisiqing123/ONOTE

---
license: mit

task_categories:
- image-to-text
- audio-to-text
- text-generation
- question-answering
language:
- en
- zh
tags:
- music
- symbolic-music
- optical-music-recognition
- jianpu
- guitar-tabs
- benchmark
pretty_name: ONOTE (Omnimodal Notation Objective Topology Examination)
size_categories:
- 1K<n<10K
---

# ONOTE: Omnimodal Notation Objective Topology Examination

ONOTE is a large-scale, omnimodal benchmark designed to evaluate music understanding across three major notation systems: **Western Staff**, **Jianpu (Numbered Notation)**, and **Guitar Tablature**.

## 📂 Dataset Structure

The dataset is organized into two primary sub-directories based on the notation and instrument type:

### 1. `pitch_Jianpu_dataset` (Staff & Numbered Notation)
This sub-folder focuses on Western staff and Jianpu processing.
* **Directories:**
* `Audio 0-100/`: Audio files for audio-to-symbolic transcription tests.
* `images 0-100/`: High-resolution images of Western standard staff notation.
* `simple_notation_images 0-100/`: Images of Jianpu (Numbered Musical Notation).
* **Metadata & QA Files:**
* `jianpu_metadata.json`: Ground truth for Jianpu transcription.
* `staff_metadata.json`: Ground truth for Staff transcription.
* `staff_qa_mcq.json`: Multiple-choice questions for Staff visual reasoning (VSU).
* `jianpu_qa_mcq.json`: Multiple-choice questions for Jianpu visual reasoning (VSU).

### 2. `guitar_dataset` (Guitar Tablature)
This sub-folder focuses on guitar-specific notation and performance analysis.
* **Directories:**
* `annotation/`: Performance metadata in `.jams` format.
* `audio/`: Clean acoustic guitar recordings.
* `images/`: ASCII and standard guitar tablature images.
* `simple_notes/`: JSON files containing extracted pitch sequences for guitar tabs.
* **Metadata & QA Files:**
* `guitar_qa_mcq.json`: Multiple-choice questions for Guitar Tab visual reasoning.
* `all_pitches_summary.json`: A comprehensive summary of pitch distributions across the guitar dataset.

## 🚀 Supported Tasks

| Task ID | Task Name | Data Source |
| :--- | :--- | :--- |
| **VSU** | Visual Score Understanding | `*_qa_mcq.json` + `images` |
| **CNC** | Cross-format Conversion | `images` + `metadata.json` |
| **AST** | Audio-to-Symbolic | `Audio` + `metadata.json` |
| **SMG** | Symbolic Music Generation | `all_pitches_summary.json` |