A Dataset and Benchmark for Optical Music Recognition of String Quartet Scores

• URL: http://arxiv.org/abs/2608.10978v1
• Date: Tue, 11 Aug 2026 14:35:17 GMT
• Title: A Dataset and Benchmark for Optical Music Recognition of String Quartet Scores
• Abstract summary: We introduce OpenScore String Quartet for Optical Music Recognition (OSSQ-OMR), the first dataset dedicated to multi-part OMR.<n>OSSQ-OMR pairs digitally encoded scores with their original scanned editions from IMSLP, with all images visually aligned to their transcriptions.<n>The dataset is released with score images at system and staff levels, and paired transcriptions in three encoding formats: Extended Linearized MusicXML (LMXE), **kern, and ABC.
• Score: 13.406503532826827
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Optical music recognition (OMR) transcribes music scores into digital formats. While the field has advanced significantly on monophonic and piano-form scores, multi-part score transcription remains underexplored, largely due to the absence of a suitable dataset. We introduce OpenScore String Quartet for Optical Music Recognition (OSSQ-OMR), the first dataset dedicated to multi-part OMR. Built on the OpenScore String Quartet corpus, OSSQ-OMR pairs digitally encoded scores with their original scanned editions from IMSLP, with all images visually aligned to their transcriptions. The dataset is released with score images at system and staff levels, and paired transcriptions in three encoding formats: Extended Linearized MusicXML (LMXE), **kern, and ABC. In total, OSSQ-OMR contains 24,544 system images and 98,172 staff images drawn from 116 string quartet scores. We accompany the dataset with a benchmark protocol and baseline results from two representative OMR models, evaluated across four random score-level splits with mutually exclusive test sets. Baselines reach OMR-NED as low as 3.6% on synthetic and 5.9% on scanned inputs; results reveal substantial effects of encoding and segmentation choices, with the LSTM-based baseline degrading on scanned inputs roughly 2.6 times less than the Transformer-based baseline.

Related papers

• FIGMA: Towards FIne-Grained Music retrievAl [65.98380295254817]
  Retrieving music using natural language descriptions has improved with contrastive audio-text models such as CLAP, but current systems remain limited to coarse semantic queries.<n>We show that this limitation stems from the contrastive learning objective itself: despite being trained on long captions, CLAP-based models effectively utilize only the first few tokens.<n>We propose FIGMA, a multi-view contrastive architecture that addresses this limitation by jointly optimizing global audio-text alignment and frame-level, token-wise alignment.
  arXiv  Detail & Related papers  (2026-06-04T18:05:39Z)
• Multimodal Music Recommendation System using LLMs [53.1178230380919]
  We propose a framework for session-based music recommendation that enriches the LastFM-1K dataset with three complementary signals.<n>We adopt the E4SRec framework by extending it with multimodal features and different item ID encoder backbones.<n>Our experiments show that integrating content-based features improves over ID-only baselines up to 95% in terms of Recall and 79% in terms of NDCG.
  arXiv  Detail & Related papers  (2026-05-28T15:34:12Z)
• Transcoda: End-to-End Zero-Shot Optical Music Recognition via Data-Centric Synthetic Training [13.569431145803792]
  We propose Transcoda, an OMR system built on (i) an advanced synthetic data generation pipeline, (ii) a normalization of the **kern encoding to enforce a unique normal form and (iii) grammar-based decoding to ensure the syntactic correctness of the output.<n>Transcoda achieves the best score among state of the art baselines on a newly curated benchmark of synthetically rendered scores at 18.46% OMR-NED (compared to 43.91% for the next-best system, Legato) and reduces the error rate on historical Polish scans to 63.97% OMR-NED (down from
  arXiv  Detail & Related papers  (2026-05-11T16:50:28Z)
• Memo2496: Expert-Annotated Dataset and Dual-View Adaptive Framework for Music Emotion Recognition [57.869107847456725]
  Music Emotion Recogniser (MER) research faces challenges due to limited high-quality annotated datasets and difficulties in addressing cross-track feature drift.<n>This work presents two primary contributions to address these issues.
  arXiv  Detail & Related papers  (2025-12-16T01:34:03Z)
• LEGATO: Large-scale End-to-end Generalizable Approach to Typeset OMR [42.106037880603445]
  Legato is a new end-to-end model for optical music recognition (OMR)<n>It is capable of recognizing full-page or multi-page typeset music scores and generating documents in ABC notation.<n>We conduct comprehensive experiments on a range of datasets and metrics and demonstrate that Legato outperforms the previous state of the art.
  arXiv  Detail & Related papers  (2025-06-23T19:35:59Z)
• Sheet Music Benchmark: Standardized Optical Music Recognition Evaluation [6.2874069879764]
  Sheet Music Benchmark (SMB) is a dataset of six hundred and eighty-five pages specifically designed to benchmark Optical Music Recognition (OMR) research.<n>OMR Normalized Edit Distance (OMR-NED) is a new metric tailored explicitly for evaluating OMR performance.
  arXiv  Detail & Related papers  (2025-06-12T08:42:19Z)
• LOCR: Location-Guided Transformer for Optical Character Recognition [55.195165959662795]
  We propose LOCR, a model that integrates location guiding into the transformer architecture during autoregression. We train the model on a dataset comprising over 77M text-location pairs from 125K academic document pages, including bounding boxes for words, tables and mathematical symbols. It outperforms all existing methods in our test set constructed from arXiv, as measured by edit distance, BLEU, METEOR and F-measure.
  arXiv  Detail & Related papers  (2024-03-04T15:34:12Z)
• Sheet Music Transformer: End-To-End Optical Music Recognition Beyond Monophonic Transcription [13.960714900433269]
  Sheet Music Transformer is the first end-to-end OMR model designed to transcribe complex musical scores without relying solely on monophonic strategies. Our model has been tested on two polyphonic music datasets and has proven capable of handling these intricate music structures effectively.
  arXiv  Detail & Related papers  (2024-02-12T11:52:21Z)
• A Multi-Stage Multi-Codebook VQ-VAE Approach to High-Performance Neural TTS [52.51848317549301]
  We propose a Multi-Stage, Multi-Codebook (MSMC) approach to high-performance neural TTS synthesis. A vector-quantized, variational autoencoder (VQ-VAE) based feature analyzer is used to encode Mel spectrograms of speech training data. In synthesis, the neural vocoder converts the predicted MSMCRs into final speech waveforms.
  arXiv  Detail & Related papers  (2022-09-22T09:43:17Z)
• Late multimodal fusion for image and audio music transcription [0.0]
  multimodal image and audio music transcription comprises the challenge of effectively combining the information conveyed by image and audio modalities. We study four combination approaches in order to merge, for the first time, the hypotheses regarding end-to-end OMR and AMT systems. Two of the four strategies considered significantly improve the corresponding unimodal standard recognition frameworks.
  arXiv  Detail & Related papers  (2022-04-06T20:00:33Z)
• VATT: Transformers for Multimodal Self-Supervised Learning from Raw Video, Audio and Text [60.97904439526213]
  Video-Audio-Text Transformer (VATT) takes raw signals as inputs and extracts multimodal representations that are rich enough to benefit a variety of downstream tasks. We train VATT end-to-end from scratch using multimodal contrastive losses and evaluate its performance by the downstream tasks of video action recognition, audio event classification, image classification, and text-to-video retrieval.
  arXiv  Detail & Related papers  (2021-04-22T17:07:41Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.