COCOLA: Coherence-Oriented Contrastive Learning of Musical Audio Representations
We present COCOLA (Coherence-Oriented Contrastive Learning for Audio), a contrastive learning method for musical audio representations that captures the harmonic and rhythmic coherence between samples. Our method operates at the level of the stems composing music tracks and can input features obtained via Harmonic-Percussive Separation (HPS). COCOLA allows the objective evaluation of generative models for music accompaniment generation, which are difficult to benchmark with established metrics. In this regard, we evaluate recent music accompaniment generation models, demonstrating the effectiveness of the proposed method. We release the model checkpoints trained on public datasets containing separate stems (MUSDB18-HQ, MoisesDB, Slakh2100, and CocoChorales).
Code (2)
Tasks
Contrastive LearningMusic GenerationMethods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
PHALAR: Phasors for Learned Musical Audio Representations
Stem retrieval, the task of matching missing stems to a given audio submix, is a key challenge currently limited by models that discard temporal information. We introduce PHALAR, a contrastive framework achieving a relat…
Beat TrackingContrastive timbre representations for musical instrument and synthesizer retrieval
Efficiently retrieving specific instrument timbres from audio mixtures remains a challenge in digital music production. This paper introduces a contrastive learning framework for musical instrument retrieval, enabling di…
Contrastive LearningData AugmentationAnalyzable Chain-of-Musical-Thought Prompting for High-Fidelity Music Generation
Autoregressive (AR) models have demonstrated impressive capabilities in generating high-fidelity music. However, the conventional next-token prediction paradigm in AR models does not align with the human creative process…
Music GenerationSemi-Supervised Contrastive Learning of Musical Representations
Despite the success of contrastive learning in Music Information Retrieval, the inherent ambiguity of contrastive self-supervision presents a challenge. Relying solely on augmentation chains and self-supervised positive …
Contrastive LearningInformation RetrievalMusic Information RetrievalTransfer LearningMulti-Source Contrastive Learning from Musical Audio
Contrastive learning constitutes an emerging branch of self-supervised learning that leverages large amounts of unlabeled data, by learning a latent space, where pairs of different views of the same sample are associated…
CoLAContrastive LearningGenre classificationMusic Auto-Tagging+4