神经语音模型中类人的语言偏见：Wav2Vec2.0中的语音范畴化与音位配列约束
Human-like Linguistic Biases in Neural Speech Models: Phonetic Categorization and Phonotactic Constraints in Wav2Vec2.0
AI总结：
本文借鉴人类语音感知实验，通过/l/-/r/声学连续体受控刺激研究Wav2Vec2如何解析音位配列约束，发现模型在早期Transformer层即表现出类人的音位配列可接受性偏见，且ASR微调会放大该效应。
摘要：
深度神经语音模型对音系学了解多少？现有研究已考察了这些模型对音素等个体语言单元的编码。本文研究单元之间的交互。受人类语音感知经典实验的启发，我们研究Wav2Vec2如何解析音位配列约束。我们在/l/和/r/之间的声学连续体上合成声音，并将其嵌入受控语境中，在这些语境里英语中只出现/l/、只出现/r/或两者都不出现。与人类相似，Wav2Vec2模型在处理此类模糊声音时表现出偏向音位配列上可接受范畴的倾向。通过使用简单度量在个体刺激层面分析模型内部，我们发现这种偏见出现在模型Transformer模块的早期层中。该效应在ASR微调后被放大，但在完全自监督模型中也存在。我们的方法展示了受控刺激设计如何帮助定位神经语音模型中的特定语言知识。
英文摘要：
What do deep neural speech models know about phonology? Existing work has examined the encoding of individual linguistic units such as phonemes in these models. Here we investigate interactions between units. Inspired by classic experiments on human speech perception, we study how Wav2Vec2 resolves phonotactic constraints. We synthesize sounds on an acoustic continuum between /l/ and /r/ and embed them in controlled contexts where only /l/, only /r/, or neither occur in English. Like humans, Wav2Vec2 models show a bias towards the phonotactically admissable category in processing such ambiguous sounds. Using simple measures to analyze model internals on the level of individual stimuli, we find that this bias emerges in early layers of the model's Transformer module. This effect is amplified by ASR finetuning but also present in fully self-supervised models. Our approach demonstrates how controlled stimulus designs can help localize specific linguistic knowledge in neural speech models.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
