Kadambi Prad, Mahr Tristan, Annear Lucas, Nomeland Henry, Liss Julie, Hustad Katherine, Berisha Visar
Arizona State University, USA.
University of Wisconsin-Madison, USA.
Interspeech. 2024 Sep;2024:5133-5137. doi: 10.21437/interspeech.2024-2239.
Automated goodness of pronunciation scores measure deviation from typical adult speech by first phonetically segmenting speech using forced alignment and then computing phoneme likelihoods. Care must be taken to distinguish between the impact of alignment error (a spurious signal) and true acoustic deviation on the automated score. Using mixed effects modeling, we predict , the difference between pronunciation scores computed using manual alignment ( ) versus computed using automatic forced alignments ( ). Pronunciation deviations and alignment error are both magnified in children's speech and may be influenced by factors such as phoneme position and phoneme type. Our methodology shows that alignment error has a moderate effect on , and other variables have small to no effect. Manual closely matches automatically calculated following cross utterance averaging. Thus, practical comparisons between child speakers should be very comparable across the two methods.
自动发音质量分数通过首先使用强制对齐对语音进行音素分割，然后计算音素似然性来测量与典型成人语音的偏差。必须注意区分对齐误差（虚假信号）和真实声学偏差对自动分数的影响。使用混合效应模型，我们预测使用手动对齐计算的发音分数（ ）与使用自动强制对齐计算的发音分数（ ）之间的差异 。发音偏差和对齐误差在儿童语音中都会放大，并且可能受到音素位置和音素类型等因素的影响。我们的方法表明，对齐误差对 有中等影响，而其他变量的影响很小或没有影响。经过跨话语平均后，手动 与自动计算的 非常匹配。因此，儿童说话者之间的实际比较在这两种方法之间应该非常具有可比性。
