Communication Sciences & Disorders, Syracuse University, Syracuse, New York 13244, USA.
Electrical and Computer Engineering, University of Maryland, College Park, Maryland 20742, USA.
JASA Express Lett. 2024 Feb 1;4(2). doi: 10.1121/10.0024632.
The effects of different acoustic representations and normalizations were compared for classifiers predicting perception of children's rhotic versus derhotic /ɹ/. Formant and Mel frequency cepstral coefficient (MFCC) representations for 350 speakers were z-standardized, either relative to values in the same utterance or age-and-sex data for typical /ɹ/. Statistical modeling indicated age-and-sex normalization significantly increased classifier performances. Clinically interpretable formants performed similarly to MFCCs and were endorsed for deep neural network engineering, achieving mean test-participant-specific F1-score = 0.81 after personalization and replication (σx = 0.10, med = 0.83, n = 48). Shapley additive explanations analysis indicated the third formant most influenced fully rhotic predictions.
比较了不同声学表示和归一化方法对预测儿童 r 音与 dr 音感知的分类器的影响。对 350 位发音者的共振峰和梅尔频率倒谱系数（MFCC）表示进行 z 标准化，分别相对于同一话语中的值或典型 r 音的年龄和性别数据。统计建模表明，年龄和性别归一化显著提高了分类器的性能。可临床解释的共振峰与 MFCCs 表现相似，并被推荐用于深度神经网络工程，在个性化和复制后，平均测试参与者特定的 F1 得分为 0.81（σx=0.10，中位数=0.83，n=48）。Shapley 加法解释分析表明，第三共振峰对完全 r 音预测的影响最大。
