Salvato in:
Dettagli Bibliografici
Autori principali: Hsieh, Fang-Chih, Lee, Wei-Jaw, Wang, Chun-Ping, Lee, Hung-yi, Dong, Hao-Wen, Yang, Yi-Hsuan
Natura: Preprint
Pubblicazione: 2026
Soggetti:
Accesso online:https://arxiv.org/abs/2605.21538
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866910242195898368
author Hsieh, Fang-Chih
Lee, Wei-Jaw
Wang, Chun-Ping
Lee, Hung-yi
Dong, Hao-Wen
Yang, Yi-Hsuan
author_facet Hsieh, Fang-Chih
Lee, Wei-Jaw
Wang, Chun-Ping
Lee, Hung-yi
Dong, Hao-Wen
Yang, Yi-Hsuan
contents This paper presents an overview and the technical framework of the ICME 2026 Grand Challenge on Academic Text-to-Music Generation (ATTM). Despite the rapid progress in text-to-music generation (TTM) systems, the field is currently dominated by models trained on massive proprietary datasets with industrial-scale computational resources, creating a significant barrier for academic research. To address this, the ATTM Challenge establishes a fair-play benchmark that requires participants to train generative models strictly from scratch using a standardized, CC-licensed subset of the MTG-Jamendo dataset containing only instrumental music. The challenge is divided into two tracks: the Efficiency Track (limited to 500M parameters) and the Performance Track (no parameter limit). Submissions are evaluated through a multi-stage process involving objective metrics, including Frechet Audio Distance, CLAP score, and a novel Concept Coverage Score (CCS), followed by a subjective listening test. By providing open-source baselines, preprocessing pipelines, reference captions, and public evaluation code for computing FAD and CLAP, this challenge aims to facilitate and promote TTM research in academic contexts.
format Preprint
id arxiv_https___arxiv_org_abs_2605_21538
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Academic Text-to-Music Grand Challenge: Datasets, Baselines, and Evaluation Methods
Hsieh, Fang-Chih
Lee, Wei-Jaw
Wang, Chun-Ping
Lee, Hung-yi
Dong, Hao-Wen
Yang, Yi-Hsuan
Sound
This paper presents an overview and the technical framework of the ICME 2026 Grand Challenge on Academic Text-to-Music Generation (ATTM). Despite the rapid progress in text-to-music generation (TTM) systems, the field is currently dominated by models trained on massive proprietary datasets with industrial-scale computational resources, creating a significant barrier for academic research. To address this, the ATTM Challenge establishes a fair-play benchmark that requires participants to train generative models strictly from scratch using a standardized, CC-licensed subset of the MTG-Jamendo dataset containing only instrumental music. The challenge is divided into two tracks: the Efficiency Track (limited to 500M parameters) and the Performance Track (no parameter limit). Submissions are evaluated through a multi-stage process involving objective metrics, including Frechet Audio Distance, CLAP score, and a novel Concept Coverage Score (CCS), followed by a subjective listening test. By providing open-source baselines, preprocessing pipelines, reference captions, and public evaluation code for computing FAD and CLAP, this challenge aims to facilitate and promote TTM research in academic contexts.
title Academic Text-to-Music Grand Challenge: Datasets, Baselines, and Evaluation Methods
topic Sound
url https://arxiv.org/abs/2605.21538