While existing literature relies on performance differences to uncover gender
biases in ASR models, a deeper analysis is essential to understand how gender
is encoded and utilized during transcript generation. This work investigates
the encoding and utilization of gender in the latent representations of two
transformer-based ASR models, Wav2Vec2 and HuBERT. Using linear erasure, we
demonstrate the feasibility of removing gender information from each layer of
an ASR model and show that such an intervention has minimal impacts on the ASR
performance. Additionally, our analysis reveals a concentration of gender
information within the first and last frames in the final layers, explaining
the ease of erasing gender in these layers. Our findings suggest the prospect
of creating gender-neutral embeddings that can be integrated into ASR
frameworks without compromising their efficacy.

使用线性消除的方法，本研究探讨了两个基于 transformer 的 ASR 模型 ——Wav2Vec2 和 HuBERT 中性别信息的编码和利用，并证明了从 ASR 模型的每一层中移除性别信息的可行性。此外，分析表明最终层中的第一帧和最后一帧存在大量的性别信息，解释了在这些层中消除性别的容易度。研究结果表明可以创建性别中性的嵌入，并将其整合到 ASR 框架中而不影响其效果。