用于神经音频编解码器的软频域解纠缠
Désentrelacement Fréquentiel Doux pour les Codecs Audio Neuronaux
AI总结：
针对神经音频模型表征可解释性不足的问题，提出一种结合时域信号频谱分解的解纠缠神经音频编解码器，在重建保真度与感知质量上均优于现有最优基线。
摘要：
尽管基于神经网络的模型已在音频特征提取领域取得显著进展，但所学习表征的可解释性仍是一项关键挑战。为解决该问题，解纠缠技术已被集成至离散神经音频编解码器中，用于为提取的token施加结构约束。但这类方法通常高度依赖特定数据集或任务设定。本研究提出一种解纠缠神经音频编解码器，它利用时域信号的频谱分解来提升表征的可解释性。实验评估表明，该方法在重建保真度和感知质量两方面均超越了当前最优基线模型。
英文摘要：
While neural-based models have led to significant advancements in audio feature extraction, the interpretability of the learned representations remains a critical challenge. To address this, disentanglement techniques have been integrated into discrete neural audio codecs to impose structure on the extracted tokens. However, these approaches often exhibit strong dependencies on specific datasets or task formulations. In this work, we propose a disentangled neural audio codec that leverages spectral decomposition of time-domain signals to enhance representation interpretability. Experimental evaluations demonstrate that our method surpasses a state-of-the-art baseline in both reconstruction fidelity and perceptual quality.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
