Recent work in the domain of speech enhancement has explored the use of self-supervised speech representations to aid in the training of neural speech enhancement models. However, much of this work focuses on using the deepest or final outputs of self supervised speech representation models, rather than the earlier feature encodings. The use of self supervised representations in such a way is often not fully motivated. In this work it is shown that the distance between the feature encodings of clean and noisy speech correlate strongly with psychoacoustically motivated measures of speech quality and intelligibility, as well as with human Mean Opinion Score (MOS) ratings. Experiments using this distance as a loss function are performed and improved performance over the use of STFT spectrogram distance based loss as well as other common loss functions from speech enhancement literature is demonstrated using objective measures such as perceptual evaluation of speech quality (PESQ) and short-time objective intelligibility (STOI).

翻译：近期语音增强领域的研究探索了利用自监督语音表示辅助训练神经网络语音增强模型的方法。然而，多数研究侧重于使用自监督语音表示模型的底层或最终输出特征，而非早期特征编码。此类自监督表示的应用方式往往缺乏充分的理论依据。本文研究表明，干净语音与带噪语音特征编码之间的距离与基于心理声学的语音质量和可懂度指标、以及人类主观意见评分（MOS）均存在强相关性。基于该距离的损失函数实验表明，相较于语音增强文献中常用的STFT频谱图距离损失及其他常见损失函数，本方法在客观指标（如感知语音质量评估PESQ和短时客观可懂度STOI）上取得了更优性能。