mlsanityData to 7 Oct 2026

Overlap-aware diarization: resegmentation using neural end-to-end overlapped speech detection

arXiv 1910.11646 ↗First posted 25 Oct 2019eess.AS cs.SDcited by 26

Not on the map. Why?

Abstract (arXiv)

We address the problem of effectively handling overlapping speech in a diarization system. First, we detail a neural Long Short-Term Memory-based architecture for overlap detection. Secondly, detected overlap regions are exploited in conjunction with a frame-level speaker posterior matrix to make two-speaker assignments for overlapped frames in the resegmentation step. The overlap detection module achieves state-of-the-art performance on the AMI, DIHARD, and ETAPE corpora. We apply overlap-aware resegmentation on AMI, resulting in a 20% relative DER reduction over the baseline system. While this approach is by no means an end-all solution to overlap-aware diarization, it reveals promising directions for handling overlap.

Key facts. Cited by 26 papers in the map (data through 7 Oct 2026). First posted on arXiv 25 Oct 2019.

Builds on

No reference list yet.

Built on by

Cited by year

Citing papers per year: 2021: 7; 2022: 6; 2023: 6; 2024: 5; 2025: 2.

26 papers.

Sort:

  1. 2021A Review of Speaker Diarization: Recent Advances with Deep Learningcited by 122
  2. 2023Powerset multi-class cross entropy loss for neural speaker diarizationcited by 109
  3. 2021Transcribe-to-Diarize: Neural Speaker Diarization for Unlimited Number of Speakers using End-to-End Speaker-Attributed ASRcited by 22
  4. 2021Towards Neural Diarization for Unlimited Numbers of Speakers Using Global and Local Attractorscited by 14
  5. 2021End-to-end Neural Diarization: From Transformer to Conformercited by 12
  6. 2021Three-class Overlapped Speech Detection using a Convolutional Recurrent Neural Networkcited by 8
  7. 2022Online Neural Diarization of Unlimited Numbers of Speakers Using Global and Local Attractorscited by 7
  8. 2022Target Speaker Voice Activity Detection with Transformers and Its Integration with End-to-End Neural Diarizationcited by 7
  9. 2022Overlapped speech and gender detection with WavLM pre-trained featurescited by 6
  10. 2022In search of strong embedding extractors for speaker diarisationcited by 5
  11. 2021BeamTransformer: Microphone Array-based Overlapping Speech Detectioncited by 2
  12. 2023End-to-End Integration of Speech Separation and Voice Activity Detection for Low-Latency Diarization of Telephone Conversationscited by 2
14 more
  1. 2023Joint speech and overlap detection: a benchmark over multiple audio setup and speech domainscited by 2
  2. 2021Compositional Clustering: Applications to Multi-Label Object Recognition and Speaker Identificationcited by 1
  3. 2024An Explainable Proxy Model for Multiabel Audio Segmentationcited by 1
  4. 2024End-to-End Supervised Hierarchical Graph Clustering for Speaker Diarizationcited by 1
  5. 2024A Semi-Automatic Approach to Create Large Gender- and Age-Balanced Speaker Corpora: Usefulness of Speaker Diarization & Identificationcited by 1
  6. 2024ASoBO: Attentive Beamformer Selection for Distant Speaker Diarization in Meetingscited by 1
  7. 2025Towards Robust Overlapping Speech Detection: A Speaker-Aware Progressive Approach Using WavLMcited by 1
  8. 2022Unsupervised Speaker Diarization that is Agnostic to Language, Overlap-Aware, and Tuning Freecited by 0
  9. 2022Joint Speech Activity and Overlap Detection with Multi-Exit Architecturecited by 0
  10. 2023The Newsbridge -Telecom SudParis VoxCeleb Speaker Recognition Challenge 2022 System Descriptioncited by 0
  11. 2023Towards Measuring and Scoring Speaker Diarization Fairnesscited by 0
  12. 2023Multi-microphone Automatic Speech Segmentation in Meetings Based on Circular Harmonics Featurescited by 0
  13. 2024Conversational Rubert for Detecting Competitive Interruptions in ASR-Transcribed Dialoguescited by 0
  14. 2025Robust Target Speaker Diarization and Separation via Augmented Speaker Embedding Samplingcited by 0