mlsanityData to 7 Oct 2026

DIVE: End-to-end Speech Diarization via Iterative Speaker Embedding

arXiv 2105.13802 ↗First posted 28 May 2021cs.SD cs.LG eess.AScited by 5

Not on the map. Why?

Abstract (arXiv)

We introduce DIVE, an end-to-end speaker diarization algorithm. Our neural algorithm presents the diarization task as an iterative process: it repeatedly builds a representation for each speaker before predicting the voice activity of each speaker conditioned on the extracted representations. This strategy intrinsically resolves the speaker ordering ambiguity without requiring the classical permutation invariant training loss. In contrast with prior work, our model does not rely on pretrained speaker representations and optimizes all parameters of the system with a multi-speaker voice activity loss. Importantly, our loss explicitly excludes unreliable speaker turn boundaries from training, which is adapted to the standard collar-based Diarization Error Rate (DER) evaluation. Overall, these contributions yield a system redefining the state-of-the-art on the standard CALLHOME benchmark, with 6.7% DER compared to 7.8% for the best alternative.

Key facts. Cited by 5 papers in the map (data through 7 Oct 2026). Builds on 23 of its 37 references that are in the map. First posted on arXiv 28 May 2021.

Builds on

23 of 37 references.

References · 23

  1. 2017Attention Is All You Needcited by 59,932
  2. 2014Adam: A Method for Stochastic Optimizationcited by 36,960
  3. 2016Layer Normalizationcited by 5,579
  4. 2015Delving Deep into Rectifiers: Surpassing Human-Level Performance on ImageNet Classificationcited by 3,590
  5. 2016WaveNet: A Generative Model for Raw Audiocited by 1,710
  6. 2015MUSAN: A Music, Speech, and Noise Corpuscited by 400
  7. 2016Permutation Invariant Training of Deep Models for Speaker-Independent Multi-talker Speech Separationcited by 189
  8. 2020CHiME-6 Challenge:Tackling Multispeaker Speech Recognition for Unsegmented Recordingscited by 129
  9. 2021A Review of Speaker Diarization: Recent Advances with Deep Learningcited by 122
  10. 2019End-to-End Neural Speaker Diarization with Permutation-Free Objectivescited by 86
  11. 2019End-to-End Neural Speaker Diarization with Self-attentioncited by 74
  12. 2020Wavesplit: End-to-End Speech Separation by Speaker Clusteringcited by 74
11 more
  1. 2017Speaker Diarization with LSTMcited by 73
  2. 2020End-to-End Speaker Diarization for an Unknown Number of Speakers with Encoder-Decoder Based Attractorscited by 70
  3. 2018Fully Supervised Speaker Diarizationcited by 46
  4. 2020The Third DIHARD Diarization Challengecited by 44
  5. 2020Integrating end-to-end neural and clustering-based diarization: Getting the best of both worldscited by 33
  6. 2019LSTM based Similarity Measurement with Spectral Clustering for Speaker Diarizationcited by 17
  7. 2019Discriminative Neural Clustering for Speaker Diarisationcited by 14
  8. 2020Neural Speaker Diarization with Speaker-Wise Chain Rulecited by 14
  9. 2020Online End-to-End Neural Diarization with Speaker-Tracing Buffercited by 13
  10. 2020End-to-End Speaker Diarization as Post-Processingcited by 13
  11. 2020End-to-End Neural Diarization: Reformulating Speaker Diarization as Simple Multi-label Classificationcited by 12

Built on by

Cited by year

Citing papers per year: 2022: 3; 2023: 1; 2024: 1.

5 papers.

  1. 2022Online Neural Diarization of Unlimited Numbers of Speakers Using Global and Local Attractorscited by 7
  2. 2022Self-supervised Speaker Diarizationcited by 3
  3. 2023End-to-End Integration of Speech Separation and Voice Activity Detection for Low-Latency Diarization of Telephone Conversationscited by 2
  4. 2024Speakers Unembedded: Embedding-free Approach to Long-form Neural Diarizationcited by 1
  5. 2022Collar-aware Training for Streaming Speaker Change Detection in Broadcast Speechcited by 0