arXiv Open Access 2025

Improving Perceptual Audio Aesthetic Assessment via Triplet Loss and Self-Supervised Embeddings

Dyah A. M. G. Wisnu Ryandhimas E. Zezario Stefano Rini Hsin-Min Wang Yu Tsao
Lihat Sumber

Abstrak

We present a system for automatic multi-axis perceptual quality prediction of generative audio, developed for Track 2 of the AudioMOS Challenge 2025. The task is to predict four Audio Aesthetic Scores--Production Quality, Production Complexity, Content Enjoyment, and Content Usefulness--for audio generated by text-to-speech (TTS), text-to-audio (TTA), and text-to-music (TTM) systems. A main challenge is the domain shift between natural training data and synthetic evaluation data. To address this, we combine BEATs, a pretrained transformer-based audio representation model, with a multi-branch long short-term memory (LSTM) predictor and use a triplet loss with buffer-based sampling to structure the embedding space by perceptual similarity. Our results show that this improves embedding discriminability and generalization, enabling domain-robust audio quality assessment without synthetic training data.

Topik & Kata Kunci

Penulis (5)

D

Dyah A. M. G. Wisnu

R

Ryandhimas E. Zezario

S

Stefano Rini

H

Hsin-Min Wang

Y

Yu Tsao

Format Sitasi

Wisnu, D.A.M.G., Zezario, R.E., Rini, S., Wang, H., Tsao, Y. (2025). Improving Perceptual Audio Aesthetic Assessment via Triplet Loss and Self-Supervised Embeddings. https://arxiv.org/abs/2509.03292

Akses Cepat

Lihat di Sumber
Informasi Jurnal
Tahun Terbit
2025
Bahasa
en
Sumber Database
arXiv
Akses
Open Access ✓