Self-supervised speech models have grown fast during the past few years and
have proven feasible for use in various downstream tasks. Some recent work has
started to look at the characteristics of these models, yet many concerns have
not been fully addressed. In this work, we conduct a study on emotional corpora
to explore a popular self-supervised model -- wav2vec 2.0. Via a set of
quantitative analysis, we mainly demonstrate that: 1) wav2vec 2.0 appears to
discard paralinguistic information that is less useful for word recognition
purposes; 2) for emotion recognition, representations from the middle layer
alone perform as well as those derived from layer averaging, while the final
layer results in the worst performance in some cases; 3) current
self-supervised models may not be the optimal solution for downstream tasks
that make use of non-lexical features. Our work provides novel findings that
will aid future research in this area and theoretical basis for the use of
existing models.

本研究通过定量分析情感语料库探索了一种流行的自我监督模型 ——wav2vec 2.0，主要证明了：1）wav2vec 2.0 似乎会丢弃不太有用于词汇识别的语用信息；2）对于情感识别，只使用中间层的表示与对多个层求平均后的表示效果相当，在某些情况下，只使用最后一层的表示效果最差；3）现有的自我监督模型可能不是利用非词汇特征的下游任务的最佳解决方案，为该领域未来的研究提供新的发现和理论基础。