In this paper, we propose a fully supervised speaker diarization approach,
named unbounded interleaved-state recurrent neural networks (UIS-RNN). Given
extracted speaker-discriminative embeddings (a.k.a. d-vectors) from input
utterances, each individual speaker is modeled by a parameter-sharing RNN,
while the RNN states for different speakers interleave in the time domain. This
RNN is naturally integrated with a distance-dependent Chinese restaurant
process (ddCRP) to accommodate an unknown number of speakers. Our system is
fully supervised and is able to learn from examples where time-stamped speaker
labels are annotated. We achieved a 7.6% diarization error rate on NIST SRE
2000 CALLHOME, which is better than the state-of-the-art method using spectral
clustering. Moreover, our method decodes in an online fashion while most
state-of-the-art systems rely on offline clustering.

本文提出了一种全监督的说话人分离方法，称为无限交错状态循环神经网络（UIS-RNN），通过 RNN 建模不同说话人，运用了 ddCRP 解决未知说话人数量问题，并实现在线分离。在 NIST SRE 2000 CALLHOME 上，其检测率为 7.6%，优于现有最先进的基于谱聚类的分离方法。