mlsanityData to 7 Oct 2026

Spot the conversation: speaker diarisation in the wild

arXiv 2007.01216 ↗First posted 2 Jul 2020cs.SD cs.CV eess.AScited by 75

Not on the map. Why?

Abstract (arXiv)

The goal of this paper is speaker diarisation of videos collected 'in the wild'. We make three key contributions. First, we propose an automatic audio-visual diarisation method for YouTube videos. Our method consists of active speaker detection using audio-visual methods and speaker verification using self-enrolled speaker models. Second, we integrate our method into a semi-automatic dataset creation pipeline which significantly reduces the number of hours required to annotate videos with diarisation labels. Finally, we use this pipeline to create a large-scale diarisation dataset called VoxConverse, collected from 'in the wild' videos, which we will release publicly to the research community. Our dataset consists of overlapping speech, a large and diverse speaker pool, and challenging background conditions.

Key facts. Cited by 75 papers in the map (data through 7 Oct 2026). First posted on arXiv 2 Jul 2020.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 14; 2022: 12; 2023: 12; 2024: 16; 2025: 9; 2026: 12.

75 papers.

Sort:

By area:

  1. 2021Ego4D: Around the World in 3,000 Hours of Egocentric Videocited by 1,530
  2. 2021A Review of Speaker Diarization: Recent Advances with Deep Learningcited by 122
  3. 2021VisualVoice: Audio-Visual Speech Separation with Cross-Modal Consistencycited by 114
  4. 2023Powerset multi-class cross entropy loss for neural speaker diarizationcited by 109
  5. 2022Visual Speech Recognition for Multiple Languages in the Wildcited by 94
  6. 2023A Light Weight Model for Active Speaker Detectioncited by 39
  7. 2021MAAS: Multi-modal Assignation for Active Speaker Detectioncited by 35
  8. 2021UniCon: Unified Context Network for Robust Active Speaker Detectioncited by 27
  9. 2022Egocentric Deep Multi-Channel Audio-Visual Active Speaker Localizationcited by 27
  10. 2021AVA-AVD: Audio-Visual Speaker Diarization in the Wildcited by 24
  11. 2023LoCoNet: Long-Short Context Network for Active Speaker Detectioncited by 24
  12. 2021Look Who's Talking: Active Speaker Detection in the Wildcited by 21
38 more
  1. 2023Egocentric Auditory Attention Localization in Conversationscited by 18
  2. 2023TalkNCE: Improving Active Speaker Detection with Talk-Aware Contrastive Learningcited by 15
  3. 2024StoryTeller: Improving Long Video Description through Global Audio-Visual Character Identificationcited by 13
  4. 2024Sortformer: A Novel Approach for Permutation-Resolved Speaker Supervision in Speech-to-Text Systemscited by 12
  5. 2022Rethinking Audio-visual Synchronization for Active Speaker Detectioncited by 9
  6. 2024The VoxCeleb Speaker Recognition Challenge: A Retrospectivecited by 9
  7. 2021Three-class Overlapped Speech Detection using a Convolutional Recurrent Neural Networkcited by 8
  8. 2023VoxSRC 2022: The Fourth VoxCeleb Speaker Recognition Challengecited by 8
  9. 2024Look, Listen and Recognise: Character-Aware Audio-Visual Subtitlingcited by 8
  10. 2025Web-Scale Collection of Video Data for 4D Animal Reconstructioncited by 8
  11. 2021USTC-NELSLIP System Description for DIHARD-III Challengecited by 7
  12. 2022Using Active Speaker Faces for Diarization in TV showscited by 7
  13. 2022Target Speaker Voice Activity Detection with Transformers and Its Integration with End-to-End Neural Diarizationcited by 7
  14. 2024A Benchmark for Multi-speaker Anonymizationcited by 7
  15. 2021Multi-scale speaker embedding-based graph attention networks for speaker diarisationcited by 6
  16. 2023Supervised Hierarchical Clustering using Graph Neural Networks for Speaker Diarizationcited by 6
  17. 2025LASER: Lip Landmark Assisted Speaker Detection for Robustnesscited by 6
  18. 2022In search of strong embedding extractors for speaker diarisationcited by 5
  19. 2023WASD: A Wilder Active Speaker Detection Datasetcited by 5
  20. 2024ASDnB: Merging Face with Body Cues For Robust Active Speaker Detectioncited by 5
  21. 2025Revisiting Active Speaker Detection: An In-the-Wild Benchmark for Generalization and Robustnesscited by 5
  22. 2021Adapting Speaker Embeddings for Speaker Diarisationcited by 4
  23. 2021FaVoA: Face-Voice Association Favours Ambiguous Speaker Detectioncited by 4
  24. 2022Large-scale learning of generalised representations for speaker recognitioncited by 4
  25. 2023Summary of the DISPLACE Challenge 2023 - DIarization of SPeaker and LAnguage in Conversational Environmentscited by 4
  26. 2025AMUSE: Audio-Visual Benchmark and Alignment Framework for Agentic Multi-Speaker Understandingcited by 4
  27. 2022Magnitude-aware Probabilistic Speaker Embeddingscited by 3
  28. 2022BER: Balanced Error Rate For Speaker Diarizationcited by 3
  29. 2023Neural Diarization with Non-autoregressive Intermediate Attractorscited by 3
  30. 2024Mamba-based Segmentation Model for Speaker Diarizationcited by 3
  31. 2025SDBench: A Comprehensive Benchmark Suite for Speaker Diarizationcited by 3
  32. 2024Integrating Audio, Visual, and Semantic Information for Enhanced Multimodal Speaker Diarizationcited by 2
  33. 2024Character-aware audio-visual subtitling in contextcited by 2
  34. 2021Scalable Data Annotation Pipeline for High-Quality Large Speech Datasets Developmentcited by 1
  35. 2022Unsupervised active speaker detection in media content using cross-modal informationcited by 1
  36. 2023Probabilistic Back-ends for Online Speaker Recognition and Clusteringcited by 1
  37. 2024End-to-End Supervised Hierarchical Graph Clustering for Speaker Diarizationcited by 1
  38. 2024Systematic Evaluation of Online Speaker Diarization Systems Regarding their Latencycited by 1

50 most cited of 75 All 75 (JSON)