# Geodesic interpolation of frame-wise speaker embeddings for the diarization of meeting scenarios

arXiv: https://arxiv.org/abs/2401.03963 · HTML: https://mlsanity.com/paper/2401.03963/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in Speech and audio distillation, one of 12 directions in Knowledge distillation.
- Builds on 18 of its 27 references that are in the map.
- First posted on arXiv 8 Jan 2024.

## Placed in

- Knowledge distillation / [Speech and audio distillation](https://mlsanity.com/distill/speech-and-audio-distillation/)

## Builds on (most cited first, 18 of 18)

- [MUSAN: A Music, Speech, and Noise Corpus](https://mlsanity.com/paper/1510.08484/) (2015)
- [End-to-end speaker segmentation for overlap-aware resegmentation](https://mlsanity.com/paper/2104.04045/) (2021)
- [End-to-End Neural Speaker Diarization with Self-attention](https://mlsanity.com/paper/1909.06247/) (2019)
- [Continuous speech separation: dataset and analysis](https://mlsanity.com/paper/2001.11482/) (2020)
- [Bayesian HMM clustering of x-vector sequences (VBx) in speaker diarization: theory, implementation and analysis on standard tasks](https://mlsanity.com/paper/2012.14952/) (2020)
- [Deep Speaker: an End-to-End Neural Speaker Embedding System](https://mlsanity.com/paper/1705.02304/) (2017)
- [Auto-Tuning Spectral Clustering for Speaker Diarization Using Normalized Maximum Eigengap](https://mlsanity.com/paper/2003.02405/) (2020)
- [Large Margin Softmax Loss for Speaker Verification](https://mlsanity.com/paper/1904.03479/) (2019)
- [Overlap-aware diarization: resegmentation using neural end-to-end overlapped speech detection](https://mlsanity.com/paper/1910.11646/) (2019)
- [The CHiME-7 DASR Challenge: Distant Meeting Transcription with Multiple Devices in Diverse Scenarios](https://mlsanity.com/paper/2306.13734/) (2023)
- [DiPCo -- Dinner Party Corpus](https://mlsanity.com/paper/1909.13447/) (2019)
- [Towards Neural Diarization for Unlimited Numbers of Speakers Using Global and Local Attractors](https://mlsanity.com/paper/2107.01545/) (2021)
- [Multi-class Spectral Clustering with Overlaps for Speaker Diarization](https://mlsanity.com/paper/2011.02900/) (2020)
- [Multi-scale speaker embedding-based graph attention networks for speaker diarisation](https://mlsanity.com/paper/2110.03361/) (2021)
- [Attention-based Encoder-Decoder Network for End-to-End Neural Speaker Diarization with Target Speaker Attractor](https://mlsanity.com/paper/2305.10704/) (2023)
- [Frame-wise and overlap-robust speaker embeddings for meeting diarization](https://mlsanity.com/paper/2306.00625/) (2023)
- [Tight integration of neural- and clustering-based diarization through deep unfolding of infinite Gaussian mixture model](https://mlsanity.com/paper/2202.06524/) (2022)
- [GIST-AiTeR Speaker Diarization System for VoxCeleb Speaker Recognition Challenge (VoxSRC) 2023](https://mlsanity.com/paper/2308.07788/) (2023)

## Abstract (arXiv)

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.