English

Fully Supervised Speaker Diarization

Audio and Speech Processing 2019-02-20 v7 Machine Learning Machine Learning

Abstract

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.

Keywords

Cite

@article{arxiv.1810.04719,
  title  = {Fully Supervised Speaker Diarization},
  author = {Aonan Zhang and Quan Wang and Zhenyao Zhu and John Paisley and Chong Wang},
  journal= {arXiv preprint arXiv:1810.04719},
  year   = {2019}
}

Comments

Accepted by ICASSP 2019

R2 v1 2026-06-23T04:35:25.659Z