# Frame-wise and overlap-robust speaker embeddings for meeting diarization

arXiv: https://arxiv.org/abs/2306.00625 · HTML: https://mlsanity.com/paper/2306.00625/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 1 Jun 2023.

## Built on by (most cited first, 4 of 4)

- [Towards Robust Overlapping Speech Detection: A Speaker-Aware Progressive Approach Using WavLM](https://mlsanity.com/paper/2505.23207/) (2025)
- [Geodesic interpolation of frame-wise speaker embeddings for the diarization of meeting scenarios](https://mlsanity.com/paper/2401.03963/) (2024)
- [Leveraging Speaker Embeddings in End-to-End Neural Diarization for Two-Speaker Scenarios](https://mlsanity.com/paper/2407.01317/) (2024)
- [FASTDIAR: Frame-level speaker encoder for Streaming Diarization](https://mlsanity.com/paper/2610.02941/) (2026)

## Abstract (arXiv)

Using a Teacher-Student training approach we developed a speaker embedding extraction system that outputs embeddings at frame rate. Given this high temporal resolution and the fact that the student produces sensible speaker embeddings even for segments with speech overlap, the frame-wise embeddings serve as an appropriate representation of the input speech signal for an end-to-end neural meeting diarization (EEND) system. We show in experiments that this representation helps mitigate a well-known problem of EEND systems: when increasing the number of speakers the diarization performance drop is significantly reduced. We also introduce block-wise processing to be able to diarize arbitrarily long meetings.