Self-supervised learning (SSL) has recently emerged as a promising paradigm for training generalisable models on large-scale data in the fields of vision, text, and speech. Although SSL has been proven effective in speech and audio, its application to music audio has yet to be thoroughly explored. This is primarily due to the distinctive challenges associated with modelling musical knowledge, particularly its tonal and pitched characteristics of music. To address this research gap, we propose an acoustic Music undERstanding model with large-scale self-supervised Training (MERT), which incorporates teacher models to provide pseudo labels in the masked language modelling (MLM) style acoustic pre-training. In our exploration, we identified a superior combination of teacher models, which outperforms conventional speech and audio approaches in terms of performance. This combination includes an acoustic teacher based on Residual Vector Quantization - Variational AutoEncoder (RVQ-VAE) and a musical teacher based on the Constant-Q Transform (CQT). These teachers effectively guide our student model, a BERT-style transformer encoder, to better model music audio. In addition, we introduce an in-batch noise mixture augmentation to enhance the representation robustness. Furthermore, we explore a wide range of settings to overcome the instability in acoustic language model pre-training, which allows our designed paradigm to scale from 95M to 330M parameters. Experimental results indicate that our model can generalise and perform well on 14 music understanding tasks and attains state-of-the-art (SOTA) overall scores. The code and models are online: https://github.com/yizhilll/MERT.

翻译：自监督学习（SSL）近年来已成为视觉、文本和语音领域在大规模数据上训练可泛化模型的一种有前景的范式。尽管SSL在语音和音频中已被证明有效，但其在音乐音频中的应用尚未得到充分探索。这主要源于音乐知识建模的独特挑战，特别是其音调与音高特性。为填补这一研究空白，我们提出了一种基于大规模自监督训练的声学音乐理解模型（MERT），该模型引入教师模型，以掩码语言建模（MLM）风格的声学预训练方式提供伪标签。在我们的探索中，我们识别出一组优越的教师模型组合，其在性能上优于传统的语音与音频方法。该组合包括基于残差向量量化-变分自编码器（RVQ-VAE）的声学教师和基于常数Q变换（CQT）的音乐教师。这些教师有效指导我们的学生模型——一种BERT风格的Transformer编码器——更好地对音乐音频进行建模。此外，我们引入了一种批内噪声混合增强方法以提升表征鲁棒性。进一步地，我们探索了多种设置以克服声学语言模型预训练中的不稳定性，使所设计范式能够从9500万参数扩展至3.3亿参数。实验结果表明，我们的模型在14项音乐理解任务上具有良好的泛化能力与性能，并取得了总体最优（SOTA）评分。代码与模型已公开：https://github.com/yizhilll/MERT。