ART-NAD：基于发音逆变换的神经声学距离用于病理语音可懂度评估
ART-NAD: An Articulatory Inversion-based Neural Acoustic Distance for Pathological Speech Intelligibility Assessment
浏览论文内容
中文总结 AI 辅助
针对病理语音可懂度评估，提出ART-NAD，用可解释的声道变量替换NAD的黑盒特征，在保持同等相关性（r=0.71）的同时提供发音偏差的可视化解释。
中文摘要 AI 辅助
面向言语病理患者的语音评估工具若要在临床实践中得到采用，必须既准确又可解释。现有的参考音频度量，如神经声学距离（NAD），与听者可懂度评分达到较高的说话者级相关性，但操作在难以解释的自监督特征上，仅提供帧级解释。我们提出ART-NAD，一种参考音频可懂度度量，用声道收缩变量（声道变量，TVs）替换NAD中的wav2vec2特征，这些变量由在相同wav2vec2特征上训练、与说话者无关的声学-发音逆变换模型从音频预测得到。ART-NAD计算为测试音频与一个或多个参考音频的九通道准声道变量轨迹之间的多元动态时间规整距离。在跨越六个病理语音数据集和五种语言的20个参考音频协议中，带静音裁剪的ART-NAD（ART-NAD-FA）在相同自监督骨干上达到与NAD-FA相同的平均说话者级皮尔逊相关性（两者r=0.71），且无显著逐协议差异（Wilcoxon p=0.18），并在20个协议中的6个上是最强的参考音频度量。除分数本身外，每个声道变量通道可视化哪个收缩随时间偏离参考，提供关于发音在何处崩溃的可解释信息。
英文摘要
Speech assessment tools for speakers with speech pathology must be both accurate and interpretable if they are to be adopted in clinical practice. Existing reference-audio measures such as the Neural Acoustic Distance (NAD) reach high speaker-level correlations with listener intelligibility scores but operate on self-supervised features that are hard to interpret, providing only frame-level explanations. We propose ART-NAD, a reference-audio intelligibility metric that replaces the \texttt{wav2vec2} features of NAD with vocal-tract constriction variables (tract variables, TVs) predicted from audio by a speaker-independent acoustic-to-articulatory inversion model trained on the same \texttt{wav2vec2} features. ART-NAD is computed as the multivariate Dynamic Time Warping distance between the nine-channel quasi-TV trajectories of the test and one or more references. Across 20 reference-audio protocols spanning six pathological-speech datasets and five languages, ART-NAD with silence trimming (ART-NAD-FA) reaches the same average speaker-level Pearson correlation as NAD-FA (both $r=0.71$) on the same self-supervised backbone, with no significant per-protocol difference (Wilcoxon $p=0.18$), and is the strongest reference-audio metric on 6 of the 20 protocols. Beside the score itself, each TV channel visualizes which constriction deviates from the reference over time, providing interpretable information as to where articulation breaks down.
发表机构
- Nagoya University（名古屋大学）
- University of Cologne（科隆大学）
- University of Groningen（格罗宁根大学）
机构由 AI 辅助整理，请以论文原文为准。
