With the advent of general-purpose speech representations from large-scale self-supervised models, applying a single model to multiple downstream tasks is becoming a de-facto approach. However, the pooling problem remains; the length of speech representations is inherently variable. The naive average pooling is often used, even though it ignores the characteristics of speech, such as differently lengthed phonemes. Hence, we design a novel pooling method to squash acoustically similar representations via vector quantization, which does not require additional training, unlike attention-based pooling. Further, we evaluate various unsupervised pooling methods on various self-supervised models. We gather diverse methods scattered around speech and text to evaluate on various tasks: keyword spotting, speaker identification, intent classification, and emotion recognition. Finally, we quantitatively and qualitatively analyze our method, comparing it with supervised pooling methods.

翻译：随着大规模自监督模型带来的通用语音表征的普及，将单一模型应用于多个下游任务正成为主流方法。然而，池化问题仍然存在：语音表征的长度具有天然可变性。尽管语音具有不同时长的音素等特征被忽略，平均池化仍常被使用。为此，我们设计了一种新颖的池化方法，通过矢量量化压缩声学相似的表征，该方法无需像基于注意力的池化那样进行额外训练。进一步地，我们在多种自监督模型上评估了各类无监督池化方法。通过收集分散在语音和文本领域的多样化方法，我们针对关键词检测、说话人识别、意图分类和情感识别等任务进行了评估。最终，我们对所提方法进行了定量与定性分析，并与监督池化方法进行了比较。