Speaker embedding models that utilize neural networks to map utterances to a
space where distances reflect similarity between speakers have driven recent
progress in the speaker recognition task. However, there is still a significant
performance gap between recognizing speakers in the training set and unseen
speakers. The latter case corresponds to the few-shot learning task, where a
trained model is evaluated on unseen classes. Here, we optimize a speaker
embedding model with prototypical network loss (PNL), a state-of-the-art
approach for the few-shot image classification task. The resulting embedding
model outperforms the state-of-the-art triplet loss based models in both
speaker verification and identification tasks, for both seen and unseen
speakers.

本研究通过利用神经网络将话语映射到一个距离反映说话人相似度的空间中的讲话人嵌入模型，优化了一种使用典型网络损失（PNL）的讲话人嵌入模型，从而优于基于三元组损失的模型，在见过和没见过讲话人的情况下，都能够在讲话人验证和识别任务中取得更好的性能