Evaluating Pretrained Music Embeddings for Cross-Performance Jazz Standard Recognition

• URL: http://arxiv.org/abs/2607.00777v1
• Date: Wed, 01 Jul 2026 11:04:28 GMT
• Title: Evaluating Pretrained Music Embeddings for Cross-Performance Jazz Standard Recognition
• Abstract summary: Jazz Trio Database is a curated subset of the Jazz Trio Database designed for cross-performance standard recognition.<n>We compare a from-scratch trained Harmonic CNN baseline against frozen pretrained music representations from recent music understanding foundation models.<n>Our results suggest that from-scratch spectrogram models overfit strongly to training performances, while pretrained embeddings provide better top-$k$ results but are sensitive to performer identity.
• Score: 0.0
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Recognizing jazz standards from audio is a challenging form of tune-level music retrieval: different performances of the same standard may vary in tempo, key, arrangement, instrumentation, improvisational content, and even whether the head melody is present. We study this problem using a curated subset of the Jazz Trio Database designed for cross-performance standard recognition. We compare a from-scratch trained Harmonic CNN baseline against frozen pretrained music representations from recent music understanding foundation models, using both supervised probing and nearest-neighbor retrieval. Our results suggest that from-scratch spectrogram models overfit strongly to training performances, while pretrained embeddings provide better top-$k$ results but are sensitive to performer identity, which can be partially reduced with a lightweight contrastive projection. Our findings motivate jazz standard recognition as a useful stress test for music representation models and as a step toward retrieval-based standard identification. Project page: https://github.com/cagries/tipofmyear.

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)
• 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)
• Scaling Self-Supervised Representation Learning for Symbolic Piano Performance [52.661197827466886]
  We study the capabilities of generative autoregressive transformer models trained on large amounts of symbolic solo-piano transcriptions.<n>We use a comparatively smaller, high-quality subset to finetune models to produce musical continuations, perform symbolic classification tasks, and produce general-purpose contrastive MIDI embeddings.
  arXiv  Detail & Related papers  (2025-06-30T14:00:14Z)
• From Generality to Mastery: Composer-Style Symbolic Music Generation via Large-Scale Pre-training [4.7205815347741185]
  We investigate how general music knowledge learned from a broad corpus can enhance the mastery of specific composer styles.<n>First, we pre-train a REMI-based music generation model on a large corpus of pop, folk, and classical music.<n>Then, we fine-tune it on a small, human-verified dataset from four renowned composers, namely Bach, Mozart, Beethoven, and Chopin.
  arXiv  Detail & Related papers  (2025-06-20T22:20:59Z)
• Analyzable Chain-of-Musical-Thought Prompting for High-Fidelity Music Generation [10.643965544581683]
  We introduce MusiCoT, a novel chain-of-thought (CoT) prompting technique tailored for music generation.<n>MusiCoT empowers the AR model to first outline an overall music structure before generating audio tokens.<n>Our experimental results indicate that MusiCoT consistently achieves superior performance across both objective and subjective metrics.
  arXiv  Detail & Related papers  (2025-03-25T12:51:21Z)
• Zero-shot Musical Stem Retrieval with Joint-Embedding Predictive Architectures [3.463789345862036]
  We introduce a new method based on Joint-Embedding Predictive Architectures, where an encoder and a predictor are jointly trained to produce latent representations of a context.<n>In particular, we design our predictor to be conditioned on arbitrary instruments, enabling our model to perform zero-shot stem retrieval.<n>We validate the retrieval performances of our model using the MUSDB18 and MoisesDB datasets.
  arXiv  Detail & Related papers  (2024-11-29T16:11:47Z)
• MuseBarControl: Enhancing Fine-Grained Control in Symbolic Music Generation through Pre-Training and Counterfactual Loss [51.85076222868963]
  We introduce a pre-training task designed to link control signals directly with corresponding musical tokens. We then implement a novel counterfactual loss that promotes better alignment between the generated music and the control prompts.
  arXiv  Detail & Related papers  (2024-07-05T08:08:22Z)
• Self-Supervised Contrastive Learning for Robust Audio-Sheet Music Retrieval Systems [3.997809845676912]
  We show that self-supervised contrastive learning can mitigate the scarcity of annotated data from real music content. We employ the snippet embeddings in the higher-level task of cross-modal piece identification. In this work, we observe that the retrieval quality improves from 30% up to 100% when real music data is present.
  arXiv  Detail & Related papers  (2023-09-21T14:54:48Z)
• 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)
• The Jazz Transformer on the Front Line: Exploring the Shortcomings of AI-composed Music through Quantitative Measures [36.49582705724548]
  This paper presents the Jazz Transformer, a generative model that utilizes a neural sequence model called the Transformer-XL for modeling lead sheets of Jazz music. We then conduct a series of computational analysis of the generated compositions from different perspectives. Our work presents in an analytical manner why machine-generated music to date still falls short of the artwork of humanity, and sets some goals for future work on automatic composition to further pursue.
  arXiv  Detail & Related papers  (2020-08-04T03:32:59Z)
• Music Gesture for Visual Sound Separation [121.36275456396075]
  "Music Gesture" is a keypoint-based structured representation to explicitly model the body and finger movements of musicians when they perform music. We first adopt a context-aware graph network to integrate visual semantic context with body dynamics, and then apply an audio-visual fusion model to associate body movements with the corresponding audio signals.
  arXiv  Detail & Related papers  (2020-04-20T17:53:46Z)

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.