The ICASSP 2026 Automatic Song Aesthetics Evaluation Challenge

TL;DR

The ICASSP 2026 ASAE Challenge aims to evaluate AI-generated songs' aesthetic quality, fostering progress in aligning automated metrics with human musical preferences through a standardized benchmark.

Contribution

This paper introduces a new challenge with two tracks for predicting subjective aesthetic scores of AI-generated music, establishing a benchmark for future research.

Findings

Top systems outperformed baseline significantly

Progress in human-aligned music evaluation methods

Established a standardized benchmark for song aesthetics

Abstract

This paper summarizes the ICASSP 2026 Automatic Song Aesthetics Evaluation (ASAE) Challenge, which focuses on predicting the subjective aesthetic scores of AI-generated songs. The challenge consists of two tracks: Track 1 targets the prediction of the overall musicality score, while Track 2 focuses on predicting five fine-grained aesthetic scores. The challenge attracted strong interest from the research community and received numerous submissions from both academia and industry. Top-performing systems significantly surpassed the official baseline, demonstrating substantial progress in aligning objective metrics with human aesthetic preferences. The outcomes establish a standardized benchmark and advance human-aligned evaluation methodologies for modern music generation systems.