mlsanityData to 14 Oct 2026

Adapting Speaker Embeddings for Speaker Diarisation

arXiv 2104.02879 ↗First posted 7 Apr 2021eess.AS cs.LG cs.SDcited by 4

Not on the map. Why?

Abstract (arXiv)

The goal of this paper is to adapt speaker embeddings for solving the problem of speaker diarisation. The quality of speaker embeddings is paramount to the performance of speaker diarisation systems. Despite this, prior works in the field have directly used embeddings designed only to be effective on the speaker verification task. In this paper, we propose three techniques that can be used to better adapt the speaker embeddings for diarisation: dimensionality reduction, attention-based embedding aggregation, and non-speech clustering. A wide range of experiments is performed on various challenging datasets. The results demonstrate that all three techniques contribute positively to the performance of the diarisation system achieving an average relative improvement of 25.07% in terms of diarisation error rate over the baseline.

Key facts. Cited by 4 papers in the map (data through 14 Oct 2026). Builds on 22 of its 39 references that are in the map. First posted on arXiv 7 Apr 2021.

Builds on

22 of 39 references.

References · 22

  1. 2017Attention Is All You Needcited by 60,361
  2. 2015Deep Residual Learning for Image Recognitioncited by 52,096
  3. 2016Identity Mappings in Deep Residual Networkscited by 1,965
  4. 2018VoxCeleb2: Deep Speaker Recognitioncited by 875
  5. 2017VoxCeleb: a large-scale speaker identification datasetcited by 732
  6. 2016Long Short-Term Memory-Networks for Machine Readingcited by 161
  7. 2020CHiME-6 Challenge:Tackling Multispeaker Speech Recognition for Unsegmented Recordingscited by 132
  8. 2015A Light CNN for Deep Face Representation with Noisy Labelscited by 126
  9. 2020In defence of metric learning for speaker recognitioncited by 126
  10. 2021A Review of Speaker Diarization: Recent Advances with Deep Learningcited by 124
  11. 2020Spot the conversation: speaker diarisation in the wildcited by 79
  12. 2020Target-Speaker Voice Activity Detection: a Novel Approach for Multi-Speaker Diarization in a Dinner Party Scenariocited by 68
10 more
  1. 2020The Third DIHARD Diarization Challengecited by 49
  2. 2019The Second DIHARD Diarization Challenge: Dataset, task, and baselinescited by 39
  3. 2020Clova Baseline System for the VoxCeleb Speaker Recognition Challenge 2020cited by 36
  4. 2020The ins and outs of speaker recognition: lessons from VoxSRC 2020cited by 21
  5. 2020End-to-End Speaker Diarization as Post-Processingcited by 13
  6. 2020Analysis of the BUT Diarization System for VoxConverse Challengecited by 11
  7. 2021The Hitachi-JHU DIHARD III System: Competitive End-to-End Neural Diarization and X-Vector Clustering Systems Combined by DOVER-Lapcited by 8
  8. 2020Look who's not talkingcited by 6
  9. 2019BUT System Description for DIHARD Speech Diarization Challenge 2019cited by 5
  10. 2021Online Streaming End-to-End Neural Diarization Handling Overlapping Speech and Flexible Numbers of Speakerscited by 2

Built on by

Cited by year

Citing papers per year: 2021: 2; 2022: 2.

4 papers.

  1. 2021Multi-scale speaker embedding-based graph attention networks for speaker diarisationcited by 7
  2. 2022In search of strong embedding extractors for speaker diarisationcited by 5
  3. 2022High-resolution embedding extractor for speaker diarisationcited by 1
  4. 2021Advancing the dimensionality reduction of speaker embeddings for speaker diarisation: disentangling noise and informing speech activitycited by 0