mlsanityData to 19 Oct 2026

Multi-target Extractor and Detector for Unknown-number Speaker Diarization

arXiv 2203.16007 ↗First posted 30 Mar 2022cs.SD cs.MM eess.AScited by 6

On the map: Speech and audio language models → Speaker recognition and diarization

Abstract (arXiv)

Strong representations of target speakers can help extract important information about speakers and detect corresponding temporal regions in multi-speaker conversations. In this study, we propose a neural architecture that simultaneously extracts speaker representations consistent with the speaker diarization objective and detects the presence of each speaker on a frame-by-frame basis regardless of the number of speakers in a conversation. A speaker representation (called z-vector) extractor and a time-speaker contextualizer, implemented by a residual network and processing data in both temporal and speaker dimensions, are integrated into a unified framework. Tests on the CALLHOME corpus show that our model outperforms most of the methods proposed so far. Evaluations in a more challenging case with simultaneous speakers ranging from 2 to 7 show that our model achieves 6.4% to 30.9% relative diarization error rate reductions over several typical baselines.

Key facts. Cited by 6 papers in the map (data through 19 Oct 2026). Placed in Speaker recognition and diarization, one of 11 directions in Speech and audio language models. Builds on 20 of its 42 references that are in the map. First posted on arXiv 30 Mar 2022.

Builds on

20 of 42 references.

Closest ancestors · 2

Same direction, newest first

  1. 2022Tight integration of neural- and clustering-based diarization through deep unfolding of infinite Gaussian mixture model14 Feb
  2. 2021DIVE: End-to-end Speech Diarization via Iterative Speaker Embedding28 May

Other references · 18

  1. 2017Attention Is All You Needcited by 61,180
  2. 2017Generalized End-to-End Loss for Speaker Verificationcited by 376
  3. 2019Dual-path RNN: efficient long sequence modeling for time-domain single-channel speech separationcited by 275
  4. 2016Permutation Invariant Training of Deep Models for Speaker-Independent Multi-talker Speech Separationcited by 247
  5. 2018Attentive Statistics Pooling for Deep Speaker Embeddingcited by 207
  6. 2019End-to-End Neural Speaker Diarization with Permutation-Free Objectivescited by 158
  7. 2019End-to-End Neural Speaker Diarization with Self-attentioncited by 139
  8. 2020Target-Speaker Voice Activity Detection: a Novel Approach for Multi-Speaker Diarization in a Dinner Party Scenariocited by 133
  9. 2020End-to-End Speaker Diarization for an Unknown Number of Speakers with Encoder-Decoder Based Attractorscited by 122
  10. 2020The Third DIHARD Diarization Challengecited by 89
  11. 2019The Second DIHARD Diarization Challenge: Dataset, task, and baselinescited by 68
  12. 2018Fully Supervised Speaker Diarizationcited by 67
6 more
  1. 2019Overlap-aware diarization: resegmentation using neural end-to-end overlapped speech detectioncited by 41
  2. 2020End-to-End Speaker Diarization as Post-Processingcited by 25
  3. 2020Speaker Diarization with Region Proposal Networkcited by 24
  4. 2020End-to-End Neural Diarization: Reformulating Speaker Diarization as Simple Multi-label Classificationcited by 24
  5. 2020Speaker Diarization with Lexical Informationcited by 22
  6. 2019The Speed Submission to DIHARD II: Contributions & Lessons Learnedcited by 6

Built on by

Cited by year

Citing papers per year: 2023: 3; 2024: 3.

6 papers.

  1. 2023Attention-based Encoder-Decoder End-to-End Neural Diarization with Embedding Enhancercited by 20
  2. 2024Overview of Speaker Modeling and Its Applications: From the Lens of Deep Speaker Representation Learningcited by 19
  3. 2023Attention-based Encoder-Decoder Network for End-to-End Neural Speaker Diarization with Target Speaker Attractorcited by 14
  4. 2024Sequence-to-Sequence Neural Diarization with Automatic Speaker Detection and Representationcited by 12
  5. 2024Multi-Input Multi-Output Target-Speaker Voice Activity Detection For Unified, Flexible, and Robust Audio-Visual Speaker Diarizationcited by 9
  6. 2023End-to-end Online Speaker Diarization with Target Speaker Trackingcited by 3

Similar, not cited

Close in wording, no citation either way

  1. 2024Listening to Multi-talker Conversations: Modular and End-to-end Perspectives
  2. 2023USED: Universal Speaker Extraction and Diarization
  3. 2026Learning Speaker-Activity-Conditioned WavLM Speaker Embeddings with Real Conversational Data
  4. 2021A Review of Speaker Diarization: Recent Advances with Deep Learning
  5. 2022PRISM: Pre-trained Indeterminate Speaker Representation Model for Speaker Diarization and Speaker Verification
  6. 2025Pretraining Multi-Speaker Identification for Neural Speaker Diarization
  7. 2024Leveraging Speaker Embeddings in End-to-End Neural Diarization for Two-Speaker Scenarios
  8. 2021X-Vectors with Multi-Scale Aggregation for Speaker Diarization