Geodesic Interpolation Of Frame-wise Speaker Embeddings For The Diarization Of Meeting Scenarios

Abstract

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.

Stats

• citations4
• S2 citations—
• github stars0
• HF likes0
• heat score5.24
• arxiv keycordlandwehr2024geodesic

Related papers

• Joint Training Of Speaker Embedding Extractor, Speech And Overlap Detection For Diarization (2024)2.26
• Multi-class Spectral Clustering With Overlaps For Speaker Diarization (2020)10.35
• End-to-end Speaker Diarization As Post-processing (2020)11.08
• Speaker Embedding-aware Neural Diarization: An Efficient Framework For Overlapping Speech Diarization In Meeting Scenarios (2022)0.00
• Interrelate Training And Searching: A Unified Online Clustering Framework For Speaker Diarization (2022)6.77
• Overlap-aware Low-latency Online Speaker Diarization Based On End-to-end Local Segmentation (2021)10.35
• Leveraging Speaker Embeddings In End-to-end Neural Diarization For Two-speaker Scenarios (2024)0.00
• Compositional Embedding Models For Speaker Identification And Diarization With Simultaneous Speech From 2+ Speakers (2020)3.58