Human listeners effortlessly compensate for phonological changes during speech perception, often unconsciously inferring the intended sounds. For example, listeners infer the underlying /n/ when hearing an utterance such as "clea[m] pan", where [m] arises from place assimilation to the following labial [p]. This article explores how the neural speech recognition model Wav2Vec2 perceives assimilated sounds, and identifies the linguistic knowledge that is implemented by the model to compensate for assimilation during Automatic Speech Recognition (ASR). Using psycholinguistic stimuli, we systematically analyze how various linguistic context cues influence compensation patterns in the model's output. Complementing these behavioral experiments, our probing experiments indicate that the model shifts its interpretation of assimilated sounds from their acoustic form to their underlying form in its final layers. Finally, our causal intervention experiments suggest that the model relies on minimal phonological context cues to accomplish this shift. These findings represent a step towards better understanding the similarities and differences in phonological processing between neural ASR models and humans.

翻译：人类听者在语音感知过程中能够毫不费力地补偿音位变化，常常无意识地推断目标音素。例如，当听到"clea[m] pan"这样的发音时（其中[m]是因后续唇音[p]而产生的部位同化），听者会推断出底层的/n/音。本文探讨了神经语音识别模型Wav2Vec2如何感知同化音素，并识别了该模型在自动语音识别（ASR）过程中为补偿同化现象所实现的语言学知识。通过采用心理语言学刺激材料，我们系统分析了不同语言学语境线索如何影响模型输出中的补偿模式。作为行为实验的补充，我们的探测实验表明：模型在最终层会将同化音素的解读从声学形式转换为底层形式。最后，我们的因果干预实验表明，模型依赖最小化的音系学语境线索来完成这种转换。这些发现标志着我们在理解神经ASR模型与人类在音系处理方面的异同道路上迈出了重要一步。