We present Deep Speaker, a neural speaker embedding system that maps
utterances to a hypersphere where speaker similarity is measured by cosine
similarity. The embeddings generated by Deep Speaker can be used for many
tasks, including speaker identification, verification, and clustering. We
experiment with ResCNN and GRU architectures to extract the acoustic features,
then mean pool to produce utterance-level speaker embeddings, and train using
triplet loss based on cosine similarity. Experiments on three distinct datasets
suggest that Deep Speaker outperforms a DNN-based i-vector baseline. For
example, Deep Speaker reduces the verification equal error rate by 50%
(relatively) and improves the identification accuracy by 60% (relatively) on a
text-independent dataset. We also present results that suggest adapting from a
model trained with Mandarin can improve accuracy for English speaker
recognition.

Deep Speaker 是一种神经说话人嵌入系统，可以将话语映射到一个超球上，在此球上，通过余弦相似度来度量说话人的相似性。该系统通过采用 ResCNN 和 GRU 架构提取声学特征，然后通过平均池化生成话语级别的说话人嵌入，并使用基于余弦相似度的三元组损失进行训练。实验表明，Deep Speaker 优于基于 DNN 的 i 矢量基线，在三个不同数据集上表现出色，还表明适应普通话训练的模型可以提高对英语说话人的识别精度。