Discriminative Neural Clustering for Speaker Diarisation
Abstract
In this paper, we propose Discriminative Neural Clustering (DNC) that formulates data clustering with a maximum number of clusters as a supervised sequence-to-sequence learning problem. Compared to traditional unsupervised clustering algorithms, DNC learns clustering patterns from training data without requiring an explicit definition of a similarity measure. An implementation of DNC based on the Transformer architecture is shown to be effective on a speaker diarisation task using the challenging AMI dataset. Since AMI contains only 147 complete meetings as individual input sequences, data scarcity is a significant issue for training a Transformer model for DNC. Accordingly, this paper proposes three data augmentation schemes: sub-sequence randomisation, input vector randomisation, and Diaconis augmentation, which generates new data samples by rotating the entire input sequence of L2-normalised speaker embeddings. Experimental results on AMI show that DNC achieves a reduction in speaker error rate (SER) of 29.4% relative to spectral clustering.
Cite
@article{arxiv.1910.09703,
title = {Discriminative Neural Clustering for Speaker Diarisation},
author = {Qiujia Li and Florian L. Kreyssig and Chao Zhang and Philip C. Woodland},
journal= {arXiv preprint arXiv:1910.09703},
year = {2020}
}
Comments
Accepted as a conference paper at the 8th IEEE Spoken Language Technology Workshop (SLT 2021)