mlsanityData to 14 Oct 2026

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

arXiv 2401.03963 ↗First posted 8 Jan 2024eess.AScited by 0

On the map: Knowledge distillation → Speech and audio distillation

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.

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.

Builds on

18 of 27 references.

References · 18

  1. 2015MUSAN: A Music, Speech, and Noise Corpuscited by 425
  2. 2021End-to-end speaker segmentation for overlap-aware resegmentationcited by 80
  3. 2019End-to-End Neural Speaker Diarization with Self-attentioncited by 77
  4. 2020Continuous speech separation: dataset and analysiscited by 74
  5. 2020Bayesian HMM clustering of x-vector sequences (VBx) in speaker diarization: theory, implementation and analysis on standard taskscited by 73
  6. 2017Deep Speaker: an End-to-End Neural Speaker Embedding Systemcited by 58
  7. 2020Auto-Tuning Spectral Clustering for Speaker Diarization Using Normalized Maximum Eigengapcited by 36
  8. 2019Large Margin Softmax Loss for Speaker Verificationcited by 29
  9. 2019Overlap-aware diarization: resegmentation using neural end-to-end overlapped speech detectioncited by 27
  10. 2023The CHiME-7 DASR Challenge: Distant Meeting Transcription with Multiple Devices in Diverse Scenarioscited by 22
  11. 2019DiPCo -- Dinner Party Corpuscited by 20
  12. 2021Towards Neural Diarization for Unlimited Numbers of Speakers Using Global and Local Attractorscited by 15
6 more
  1. 2020Multi-class Spectral Clustering with Overlaps for Speaker Diarizationcited by 8
  2. 2021Multi-scale speaker embedding-based graph attention networks for speaker diarisationcited by 7
  3. 2023Attention-based Encoder-Decoder Network for End-to-End Neural Speaker Diarization with Target Speaker Attractorcited by 5
  4. 2023Frame-wise and overlap-robust speaker embeddings for meeting diarizationcited by 4
  5. 2022Tight integration of neural- and clustering-based diarization through deep unfolding of infinite Gaussian mixture modelcited by 3
  6. 2023GIST-AiTeR Speaker Diarization System for VoxCeleb Speaker Recognition Challenge (VoxSRC) 2023cited by 1

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2025Dissecting the Segmentation Model of End-to-End Diarization with Vector Clustering
  2. 2025Exploring Speaker Diarization with Mixture of Experts
  3. 2023A Reinforcement Learning Framework for Online Speaker Diarization
  4. 2026FASTDIAR: Frame-level speaker encoder for Streaming Diarization
  5. 2025Towards Low-Latency Tracking of Multiple Speakers With Short-Context Speaker Embeddings
  6. 2023A Teacher-Student approach for extracting informative speaker embeddings from speech mixtures
  7. 2026Unmixing The Crowd: Learning Persistent Speaker Representations from Mixture-Derived Multi-Speaker Embeddings ↗
  8. 2025Multi-Stage Speaker Diarization for Noisy Classrooms