AgentSkillsCN

Speaker Clustering Methods

读取并处理 GLM 输出文件。当您需要从 NetCDF 输出中提取温度数据、转换深度坐标，或基于观测值计算 RMSE 时，可选用此技能。

SKILL.md
--- frontmatter
name: Speaker Clustering Methods
description: Choose and implement clustering algorithms for grouping speaker embeddings after VAD and embedding extraction. Compare Hierarchical clustering (auto-tunes speaker count), KMeans (fast, requires known count), and Agglomerative clustering (fixed clusters). Use Hierarchical clustering when speaker count is unknown, KMeans when count is known, and always normalize embeddings before clustering.

Speaker Clustering Methods

When to Use

  • •After extracting speaker embeddings from VAD segments
  • •Need to group similar speakers together
  • •Determining number of speakers automatically or manually