用多核相似性构建稀疏图，实现无需预训练的顶尖语音分割
MK-SGC-SC: Multiple Kernel Guided Sparse Graph Construction in Spectral Clustering for Unsupervised Speaker Diarization
- 基于多个核函数计算说话人嵌入相似性，构建局部相似性强调的稀疏图
- 在DIHARD-III等数据集上达到当前最优无监督性能，鲁棒性强
- 方法简洁有效，适合研究无监督语音分析与聚类的学者参考
语音分割旨在将音频记录划分为对应不同说话人的区域。尽管无监督语音分割本质上具有挑战性，但无需预训练或弱监督即可识别说话人区域的研究仍极具吸引力。本文提出，通过测量说话人嵌入的多种核相似性，并以合理方式构建稀疏图用于谱聚类，即可在完全无监督设置下实现最先进的性能。具体地，采用四种多项式核和一个一阶反余弦核来度量嵌入相似性，从而构建强调局部相似性的稀疏图。实验表明，该方法在DIHARD-III、AMI和VoxConverse等多个具有挑战性的语料库中均表现优异。为促进进一步研究，代码已开源于https://github.com/nikhilraghav29/MK-SGC-SC。
原文摘要 · Abstract (English)
Speaker diarization aims to segment audio recordings into regions corresponding to individual speakers. Although unsupervised speaker diarization is inherently challenging, the prospect of identifying speaker regions without pretraining or weak supervision motivates research on clustering techniques. In this work, we share the notable observation that measuring multiple kernel similarities of speaker embeddings to thereafter craft a sparse graph for spectral clustering in a principled manner is sufficient to achieve state-of-the-art performances in a fully unsupervised setting. Specifically, we consider four polynomial kernels and a degree one arccosine kernel to measure similarities in speaker embeddings, using which sparse graphs are constructed in a principled manner to emphasize local similarities. Experiments show the proposed approach excels in unsupervised speaker diarization over a variety of challenging environments in the DIHARD-III, AMI, and VoxConverse corpora. To encourage further research, our implementations are available at https://github.com/nikhilraghav29/MK-SGC-SC.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。