CrossMuSim: A Cross-Modal Framework for Music Similarity Retrieval with LLM-Powered Text Description Sourcing and Mining

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Tsoi, Tristan, Deng, Jiajun, Ju, Yaolong, Weck, Benno, Kirchhoff, Holger, Lui, Simon
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866910963861553152
author Tsoi, Tristan
Deng, Jiajun
Ju, Yaolong
Weck, Benno
Kirchhoff, Holger
Lui, Simon
author_facet Tsoi, Tristan
Deng, Jiajun
Ju, Yaolong
Weck, Benno
Kirchhoff, Holger
Lui, Simon
contents Music similarity retrieval is fundamental for managing and exploring relevant content from large collections in streaming platforms. This paper presents a novel cross-modal contrastive learning framework that leverages the open-ended nature of text descriptions to guide music similarity modeling, addressing the limitations of traditional uni-modal approaches in capturing complex musical relationships. To overcome the scarcity of high-quality text-music paired data, this paper introduces a dual-source data acquisition approach combining online scraping and LLM-based prompting, where carefully designed prompts leverage LLMs' comprehensive music knowledge to generate contextually rich descriptions. Exten1sive experiments demonstrate that the proposed framework achieves significant performance improvements over existing benchmarks through objective metrics, subjective evaluations, and real-world A/B testing on the Huawei Music streaming platform.
format Preprint
id arxiv_https___arxiv_org_abs_2503_23128
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle CrossMuSim: A Cross-Modal Framework for Music Similarity Retrieval with LLM-Powered Text Description Sourcing and Mining
Tsoi, Tristan
Deng, Jiajun
Ju, Yaolong
Weck, Benno
Kirchhoff, Holger
Lui, Simon
Sound
Artificial Intelligence
Audio and Speech Processing
Music similarity retrieval is fundamental for managing and exploring relevant content from large collections in streaming platforms. This paper presents a novel cross-modal contrastive learning framework that leverages the open-ended nature of text descriptions to guide music similarity modeling, addressing the limitations of traditional uni-modal approaches in capturing complex musical relationships. To overcome the scarcity of high-quality text-music paired data, this paper introduces a dual-source data acquisition approach combining online scraping and LLM-based prompting, where carefully designed prompts leverage LLMs' comprehensive music knowledge to generate contextually rich descriptions. Exten1sive experiments demonstrate that the proposed framework achieves significant performance improvements over existing benchmarks through objective metrics, subjective evaluations, and real-world A/B testing on the Huawei Music streaming platform.
title CrossMuSim: A Cross-Modal Framework for Music Similarity Retrieval with LLM-Powered Text Description Sourcing and Mining
topic Sound
Artificial Intelligence
Audio and Speech Processing
url https://arxiv.org/abs/2503.23128