Quantifying Consonant Contributions to Word Intelligibility via Acoustic Masking

通过声学掩蔽量化辅音对单词可懂度的贡献

Abstract: Consonants contribute unequally to whether a word is understood. Given the limited time available for therapy, ranking consonants by contribution to intelligibility helps prioritize intervention targets in motor speech disorders. However, measuring this contribution relies on perceptual studies that are difficult to scale.

摘要： 辅音对单词是否能被理解的贡献是不均衡的。鉴于治疗时间有限，根据辅音对可懂度的贡献进行排序，有助于确定运动性言语障碍干预目标的优先级。然而，衡量这种贡献依赖于难以扩展的感知研究。

This paper presents a scalable method that measures consonant contribution using acoustic masking. We silence one consonant at a time in an isolated word and test whether an automatic speech recognition (ASR) model still recognizes the word. We define a consonant’s contribution score as the proportion of its masked instances for which the word becomes misrecognized, which we refer to as the mask-induced misrecognition rate (MMR).

本文提出了一种利用声学掩蔽来衡量辅音贡献的可扩展方法。我们在孤立单词中一次屏蔽一个辅音，并测试自动语音识别（ASR）模型是否仍能识别该单词。我们将辅音的贡献分数定义为单词因该辅音被屏蔽而导致识别错误的比例，我们将其称为掩蔽诱导识别错误率（MMR）。

We validate MMR against two linguistic factors previously reported to correlate with consonant contribution, namely phoneme frequency and functional load. We apply this analysis across four languages, English, Spanish, German, and Czech, using three ASR architectures, MMS (encoder-only), Whisper (encoder-decoder), and Qwen3-ASR (LLM-based).

我们通过两个先前被报道与辅音贡献相关的语言学因素——音素频率和功能负荷——来验证 MMR。我们使用三种 ASR 架构（MMS（仅编码器）、Whisper（编码器-解码器）和 Qwen3-ASR（基于大语言模型））对英语、西班牙语、德语和捷克语四种语言进行了此项分析。

Using partial Spearman correlations, we find that phoneme frequency correlates negatively with MMR while functional load correlates positively. In other words, more frequent consonants are less disruptive when masked, whereas consonants carrying more lexical contrast are more disruptive. Further cross-language analysis shows that consonant rankings are not consistent, indicating that consonant contribution is language-dependent.

通过偏斯皮尔曼相关性分析，我们发现音素频率与 MMR 呈负相关，而功能负荷与 MMR 呈正相关。换句话说，更频繁出现的辅音在被屏蔽时造成的干扰较小，而承载更多词汇对比的辅音在被屏蔽时造成的干扰更大。进一步的跨语言分析表明，辅音的排序并不一致，这说明辅音的贡献具有语言依赖性。