Speaker embedding has been a fundamental feature for speaker-related tasks such as verification, clustering, and diarization. Traditionally, speaker embeddings are represented as fixed vectors in high-dimensional space. This could lead to biased estimations, especially when handling shorter utterances. In this paper we propose to represent a speaker utterance as "floating" vector whose state is indeterminate without knowing the context. The state of a speaker representation is jointly determined by itself, other speech from the same speaker, as well as other speakers it is being compared to. The content of the speech also contributes to determining the final state of a speaker representation. We pre-train an indeterminate speaker representation model that estimates the state of an utterance based on the context. The pre-trained model can be fine-tuned for downstream tasks such as speaker verification, speaker clustering, and speaker diarization. Substantial improvements are observed across all downstream tasks.
翻译:发言人嵌入是诸如核查、集群和分化等与发言者有关的任务的一个基本特征,传统上,发言人嵌入是作为高维空间的固定矢量。这可能导致偏差估计,特别是在处理较短的语句时。在本文中,我们提议将发言者的发音作为“浮动”矢量,其状态不确定。发言者代表状况是由自己、同一发言者的其他发言以及与之比较的其他发言者共同决定的。演讲的内容也有助于确定发言者代表的最后状态。我们预先培训了一个不确定的演讲代表模式,根据背景估计言论的状况。预先培训的模式可以微调地适应下游任务,如发言者的核实、发言人集群和发言者的分化。所有下游任务都可以看到实质性的改进。