FIGMA: Towards FIne-Grained Music retrievAl

• URL: http://arxiv.org/abs/2606.06615v1
• Date: Thu, 04 Jun 2026 18:05:39 GMT
• Title: FIGMA: Towards FIne-Grained Music retrievAl
• Abstract summary: 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.
• Score: 65.98380295254817
• License: http://creativecommons.org/licenses/by-nc-sa/4.0/
• Abstract: 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. When descriptions specify fine-grained musical attributes such as tempo, key, chord progression, or rhythmic structure, existing models often fail to retrieve the correct audio. 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, discarding much of the information encoded in detailed prompts. Then, we propose FIGMA (FIne-Grained Music RetrievAl), a multi-view contrastive architecture that addresses this limitation by jointly optimizing global audio-text alignment and frame-level, token-wise alignment. This design enables FIGMA to capture both high-level semantic context and fine-grained musical attributes within a unified representation space. Moreover, we formalize the task of Fine-Grained Music Retrieval and construct Fine-Grained Music Caption dataset (FGMCaps), a large-scale dataset of 380K music-caption pairs for training along with a 10K test set, both annotated with tempo, key, chord progression, beat count, as well as genre and mood. Extensive experiments demonstrate that FIGMA consistently outperforms existing CLAP-based music retrieval models across multiple music retrieval benchmarks, including out-of-domain evaluations, with relative improvements of up to 73.3%.

Related papers

• Pushing the Frontier of Full-Song Generation: Hierarchical Autoregressive Planning Meets Flow-Matching Rendering [36.032642952445414]
  We present a unified song generation framework capable of producing high-quality full-length music from lyrics, text descriptions, and musical attributes.<n>The proposed framework supports three tasks: Lyrics-to-Song Generation, which generates complete songs from text descriptions, lyrics, and musical attributes; Instrumental Music Generation, which creates music without vocals; and Cover Song Generation, which reinterprets existing songs with different styles while preserving melodic content.
  arXiv  Detail & Related papers  (2026-07-22T15:11:46Z)
• Revisiting Content-Based Music Recommendation: Efficient Feature Aggregation from Large-Scale Music Models [54.4270504928356]
  Music Recommendation Systems (MRSs) are a cornerstone of modern streaming platforms.<n>We propose TASTE, a comprehensive dataset and benchmarking framework designed to highlight the role of multimodal information in music recommendation.<n>By leveraging recent large-scale self-supervised music encoders, we demonstrate the substantial value of the extracted audio representations across recommendation tasks.
  arXiv  Detail & Related papers  (2026-02-10T15:24:41Z)
• Music Flamingo: Scaling Music Understanding in Audio Language Models [98.94537017112704]
  Music Flamingo is a novel large audio-language model designed to advance music understanding in foundational audio models.<n> MF-Skills is a dataset labeled through a multi-stage pipeline that yields rich captions and question-answer pairs covering harmony, structure, timbre, lyrics, and cultural context.<n>We introduce a post-training recipe: we first cold-start with MF-Think, a novel chain-of-thought dataset grounded in music theory, followed by GRPO-based reinforcement learning with custom rewards.
  arXiv  Detail & Related papers  (2025-11-13T13:21:09Z)
• CoLLAP: Contrastive Long-form Language-Audio Pretraining with Musical Temporal Structure Augmentation [17.41880273107978]
  Contrastive Long-form Language-Audio Pretraining (textbfCoLLAP) We propose Contrastive Long-form Language-Audio Pretraining (textbfCoLLAP) to significantly extend the perception window for both the input audio (up to 5 minutes) and the language descriptions (exceeding 250 words) We collect 51.3K audio-text pairs derived from the large-scale AudioSet training dataset, where the average audio length reaches 288 seconds.
  arXiv  Detail & Related papers  (2024-10-03T07:46:51Z)
• Futga: Towards Fine-grained Music Understanding through Temporally-enhanced Generative Augmentation [18.12051302437043]
  We propose a model equipped with fined-grained music understanding capabilities through learning from generative augmentation with temporal compositions. We leverage existing music caption datasets and large language models (LLMs) to synthesize fine-grained music captions with structural descriptions and time boundaries for full-length songs.
  arXiv  Detail & Related papers  (2024-07-29T22:53:32Z)
• Music Genre Classification: A Comparative Analysis of CNN and XGBoost Approaches with Mel-frequency cepstral coefficients and Mel Spectrograms [0.0]
  This study investigates the performances of three models: a proposed convolutional neural network (CNN), the VGG16 with fully connected layers (FC), and an eXtreme Gradient Boosting (XGBoost) approach on different features. The results show that the MFCC XGBoost model outperformed the others. Furthermore, applying data segmentation in the data preprocessing phase can significantly enhance the performance of the CNNs.
  arXiv  Detail & Related papers  (2024-01-09T01:50:31Z)
• MARBLE: Music Audio Representation Benchmark for Universal Evaluation [79.25065218663458]
  We introduce the Music Audio Representation Benchmark for universaL Evaluation, termed MARBLE. It aims to provide a benchmark for various Music Information Retrieval (MIR) tasks by defining a comprehensive taxonomy with four hierarchy levels, including acoustic, performance, score, and high-level description. We then establish a unified protocol based on 14 tasks on 8 public-available datasets, providing a fair and standard assessment of representations of all open-sourced pre-trained models developed on music recordings as baselines.
  arXiv  Detail & Related papers  (2023-06-18T12:56:46Z)
• Simple and Controllable Music Generation [94.61958781346176]
  MusicGen is a single Language Model (LM) that operates over several streams of compressed discrete music representation, i.e., tokens. Unlike prior work, MusicGen is comprised of a single-stage transformer LM together with efficient token interleaving patterns.
  arXiv  Detail & Related papers  (2023-06-08T15:31:05Z)
• RMSSinger: Realistic-Music-Score based Singing Voice Synthesis [56.51475521778443]
  RMS-SVS aims to generate high-quality singing voices given realistic music scores with different note types. We propose RMSSinger, the first RMS-SVS method, which takes realistic music scores as input. In RMSSinger, we introduce word-level modeling to avoid the time-consuming phoneme duration annotation and the complicated phoneme-level mel-note alignment.
  arXiv  Detail & Related papers  (2023-05-18T03:57:51Z)
• Towards Context-Aware Neural Performance-Score Synchronisation [2.0305676256390934]
  Music synchronisation provides a way to navigate among multiple representations of music in a unified manner. Traditional synchronisation methods compute alignment using knowledge-driven and performance analysis approaches. This PhD furthers the development of performance-score synchronisation research by proposing data-driven, context-aware alignment approaches.
  arXiv  Detail & Related papers  (2022-05-31T16:45:25Z)
• MusCaps: Generating Captions for Music Audio [14.335950077921435]
  We present the first music audio captioning model, MusCaps, consisting of an encoder-decoder with temporal attention. Our method combines convolutional and recurrent neural network architectures to jointly process audio-text inputs. Our model represents a shift away from classification-based music description and combines tasks requiring both auditory and linguistic understanding.
  arXiv  Detail & Related papers  (2021-04-24T16:34:47Z)

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.