From Image to Music Language: A Two-Stage Structure Decoding Approach for Complex Polyphonic OMR

• URL: http://arxiv.org/abs/2604.20522v3
• Date: Thu, 30 Apr 2026 12:50:07 GMT
• Title: From Image to Music Language: A Two-Stage Structure Decoding Approach for Complex Polyphonic OMR
• Abstract summary: We propose a new approach for a practical two-stage Optical Music Recognition (OMR) pipeline.<n>Given symbol and event candidates from the visual pipeline, we decode them into an editable, verifiable, and exportable score structure.<n>We focus on complex polyphonic staff notation, especially piano scores, where voice separation and intra-measure timing are the main bottlenecks.
• Score: 23.454234180354323
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: We propose a new approach for a practical two-stage Optical Music Recognition (OMR) pipeline, with a particular focus on its second stage. Given symbol and event candidates from the visual pipeline, we decode them into an editable, verifiable, and exportable score structure. We focus on complex polyphonic staff notation, especially piano scores, where voice separation and intra-measure timing are the main bottlenecks. Our approach formulates second-stage decoding as a structure decoding problem and uses topology recognition with probability-guided search (BeadSolver) as its core method. We also describe a data strategy that combines procedural generation with recognition-feedback annotations. The result is a practical decoding component for real OMR systems and a path to accumulate structured score data for future end-to-end, multimodal, and RL-style methods.

Related papers

• Hierarchical Semantic-Constrained Heterogeneous Graph for Audio-Visual Event Localization [69.67186845167568]
  Open-vocabulary audio-visual event localization (OV-AVEL) jointly models audio-visual cues to recognize and temporally localize events.<n>Existing methods primarily learn joint audio-visual representations in Euclidean space.<n>We propose a hierarchical semantic constrained heterogeneous graph (HSCHG) for audio-visual event localization framework.
  arXiv  Detail & Related papers  (2026-06-05T08:23:58Z)
• Text-Queried Audio Source Separation via Hierarchical Modeling [53.94434504259829]
  We propose a hierarchical decomposition framework, HSM-TSS, that decouples the task into global-local semantic-guided feature separation and structure-preserving acoustic reconstruction.<n>A Q-Audio architecture is employed to align audio and text modalities, serving as pretrained global-semantic encoders.<n>Our method achieves state-of-the-art separation performance with data-efficient training while maintaining superior semantic consistency with queries in complex auditory scenes.
  arXiv  Detail & Related papers  (2025-05-27T11:00:38Z)
• CAV-MAE Sync: Improving Contrastive Audio-Visual Mask Autoencoders via Fine-Grained Alignment [76.32508013503653]
  We propose CAV-MAE Sync as a simple yet effective extension of the original CAV-MAE framework for self-supervised audio-visual learning.<n>We tackle the mismatch between modalities by treating audio as a temporal sequence aligned with video frames, rather than using global representations.<n>We improve spatial localization by introducing learnable register tokens that reduce semantic load on patch tokens.
  arXiv  Detail & Related papers  (2025-05-02T12:59:58Z)
• End-to-End Real-World Polyphonic Piano Audio-to-Score Transcription with Hierarchical Decoding [4.604877755214193]
  Existing end-to-end piano A2S systems have been trained and evaluated with only synthetic data. We propose a sequence-to-sequence (Seq2Seq) model with a hierarchical decoder that aligns with the hierarchical structure of musical scores. We propose a two-stage training scheme, which involves pre-training the model using an expressive performance rendering system on synthetic audio, followed by fine-tuning the model using recordings of human performance.
  arXiv  Detail & Related papers  (2024-05-22T10:52:04Z)
• Improving Audio-Visual Speech Recognition by Lip-Subword Correlation Based Visual Pre-training and Cross-Modal Fusion Encoder [58.523884148942166]
  We propose two novel techniques to improve audio-visual speech recognition (AVSR) under a pre-training and fine-tuning training framework. First, we explore the correlation between lip shapes and syllable-level subword units in Mandarin to establish good frame-level syllable boundaries from lip shapes. Next, we propose an audio-guided cross-modal fusion encoder (CMFE) neural network to utilize main training parameters for multiple cross-modal attention layers.
  arXiv  Detail & Related papers  (2023-08-14T08:19:24Z)
• Lip2Vec: Efficient and Robust Visual Speech Recognition via Latent-to-Latent Visual to Audio Representation Mapping [4.271091833712731]
  We propose a simple approach, named Lip2Vec that is based on learning a prior model. The proposed model compares favorably with fully-supervised learning methods on the LRS3 dataset achieving 26 WER. We believe that reprogramming the VSR as an ASR task narrows the performance gap between the two and paves the way for more flexible formulations of lip reading.
  arXiv  Detail & Related papers  (2023-08-11T12:59:02Z)
• 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)
• Learning Audio Representations with MLPs [2.0418546897282095]
  We propose an efficient-based approach for learning audio representations namely timestamp and scene-level audio embeddings. We use an encoder consisting of sequentially stacked gated blocks, which accept 2D MFCCs as inputs. We also provide a simple temporal-based algorithm for computing scene-level embeddings from timestamp embeddings.
  arXiv  Detail & Related papers  (2022-03-16T09:33:36Z)
• Exploring single-song autoencoding schemes for audio-based music structure analysis [6.037383467521294]
  This work explores a "piece-specific" autoencoding scheme, in which a low-dimensional autoencoder is trained to learn a latent/compressed representation specific to a given song. We report that the proposed unsupervised auto-encoding scheme achieves the level of performance of supervised state-of-the-art methods with 3 seconds tolerance.
  arXiv  Detail & Related papers  (2021-10-27T13:48:25Z)
• An Empirical Evaluation of End-to-End Polyphonic Optical Music Recognition [24.377724078096144]
  Piano and orchestral scores frequently exhibit polyphonic passages, which add a second dimension to the task. We propose two novel formulations for end-to-end polyphonic OMR. We observe a new state-of-the-art performance with our multi-sequence detection decoder, RNNDecoder.
  arXiv  Detail & Related papers  (2021-08-03T22:04:40Z)
• Any-to-Many Voice Conversion with Location-Relative Sequence-to-Sequence Modeling [61.351967629600594]
  This paper proposes an any-to-many location-relative, sequence-to-sequence (seq2seq), non-parallel voice conversion approach. In this approach, we combine a bottle-neck feature extractor (BNE) with a seq2seq synthesis module. Objective and subjective evaluations show that the proposed any-to-many approach has superior voice conversion performance in terms of both naturalness and speaker similarity.
  arXiv  Detail & Related papers  (2020-09-06T13:01:06Z)
• Unsupervised Deep Cross-modality Spectral Hashing [65.3842441716661]
  The framework is a two-step hashing approach which decouples the optimization into binary optimization and hashing function learning. We propose a novel spectral embedding-based algorithm to simultaneously learn single-modality and binary cross-modality representations. We leverage the powerful CNN for images and propose a CNN-based deep architecture to learn text modality.
  arXiv  Detail & Related papers  (2020-08-01T09:20:11Z)

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.