Meta Audiobox Aesthetics: Unified Automatic Quality Assessment for Speech, Music, and Sound
Abstrak
The quantification of audio aesthetics remains a complex challenge in audio processing, primarily due to its subjective nature, which is influenced by human perception and cultural context. Traditional methods often depend on human listeners for evaluation, leading to inconsistencies and high resource demands. This paper addresses the growing need for automated systems capable of predicting audio aesthetics without human intervention. Such systems are crucial for applications like data filtering, pseudo-labeling large datasets, and evaluating generative audio models, especially as these models become more sophisticated. In this work, we introduce a novel approach to audio aesthetic evaluation by proposing new annotation guidelines that decompose human listening perspectives into four distinct axes. We develop and train no-reference, per-item prediction models that offer a more nuanced assessment of audio quality. Our models are evaluated against human mean opinion scores (MOS) and existing methods, demonstrating comparable or superior performance. This research not only advances the field of audio aesthetics but also provides open-source models and datasets to facilitate future work and benchmarking. We release our code and pre-trained model at: https://github.com/facebookresearch/audiobox-aesthetics
Topik & Kata Kunci
Penulis (13)
Andros Tjandra
Yi-Chiao Wu
Baishan Guo
John Hoffman
Brian Ellis
Apoorv Vyas
Bowen Shi
Sanyuan Chen
Matt Le
N. Zacharov
Carleigh Wood
Ann Lee
Wei-Ning Hsu
Akses Cepat
- Tahun Terbit
- 2025
- Bahasa
- en
- Total Sitasi
- 121×
- Sumber Database
- Semantic Scholar
- DOI
- 10.48550/arXiv.2502.05139
- Akses
- Open Access ✓