Geodesic interpolation of frame-wise speaker embeddings for the diarization of meeting scenarios
ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)(2024)
摘要
We propose a modified teacher-student training for the extraction of
frame-wise speaker embeddings that allows for an effective diarization of
meeting scenarios containing partially overlapping speech. To this end, a
geodesic distance loss is used that enforces the embeddings computed from
regions with two active speakers to lie on the shortest path on a sphere
between the points given by the d-vectors of each of the active speakers. Using
those frame-wise speaker embeddings in clustering-based diarization outperforms
segment-level clustering-based diarization systems such as VBx and Spectral
Clustering. By extending our approach to a mixture-model-based diarization, the
performance can be further improved, approaching the diarization error rates of
diarization systems that use a dedicated overlap detection, and outperforming
these systems when also employing an additional overlap detection.
更多查看译文
关键词
speaker embeddings,diarization,clustering,mixture model,meeting data
AI 理解论文
溯源树
样例
生成溯源树,研究论文发展脉络
Chat Paper
正在生成论文摘要