Acoustic word embeddings are typically created by training a pooling function using pairs of word-like units. For unsupervised systems, these are mined using k-nearest neighbor (KNN) search, which is slow. Recently, mean-pooled representations from a pre-trained self-supervised English model were suggested as a promising alternative, but their performance on target languages was not fully competitive. Here, we explore improvements to both approaches: we use continued pre-training to adapt the self-supervised model to the target language, and we use a multilingual phone recognizer (MPR) to mine phone n-gram pairs for training the pooling function. Evaluating on four languages, we show that both methods outperform a recent approach on word discrimination. Moreover, the MPR method is orders of magnitude faster than KNN, and is highly data efficient. We also show a small improvement from performing learned pooling on top of the continued pre-trained representations.

翻译：声学词嵌入通常通过使用成对的类词单元训练池化函数来生成。在无监督系统中，这些单元通过k近邻（KNN）搜索挖掘，但该方法速度较慢。近期研究表明，来自预训练英语自监督模型的均值池化表示是一种有前景的替代方案，但其在目标语言上的表现尚未完全具备竞争力。本文探索了对两种方法的改进：通过持续预训练使自监督模型适应目标语言，并利用多语言语音识别器（MPR）挖掘音素n-gram对以训练池化函数。在四种语言上的评估显示，两种方法在词区分任务上均优于近期方法。此外，MPR方法比KNN快数个数量级，且具有极高的数据效率。我们还发现，在持续预训练表示之上进行学习池化能带来轻微的性能提升。